Trang chủ Khám phá Trợ giúp
Đăng nhập
Server
/
fish-speech
41
0
Fork 0
Các tập tin Các vấn đề 0 Yêu cầu khéo về 0 Wiki
Branch: gh-pages
Branches Tags
fish-speech
/
index.html

index.html 48 KB
Permalink Lịch sử Raw

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328 
  1. 

  2. <!doctype html>
    3. 

  3. <html lang="en" class="no-js">
    4. 

  4.   <head>
    5. 

  5.     
    6. 

  6.       <meta charset="utf-8">
    7. 

  7.       <meta name="viewport" content="width=device-width,initial-scale=1">
    8. 

  8.       
    9. 

  9.         <meta name="description" content="Targeting SOTA TTS solutions.">
    10. 

  10.       
    11. 

  11.       
    12. 

  12.       
    13. 

  13.         <link rel="canonical" href="https://speech.fish.audio/">
    14. 

  14.       
    15. 

  15.       
    16. 

  16.       
    17. 

  17.         <link rel="next" href="install/">
    18. 

  18.       
    19. 

  19.       
    20. 

  20.         
    21. 

  21.           <link rel="alternate" href="/" hreflang="en">
    22. 

  22.         
    23. 

  23.           <link rel="alternate" href="/zh/" hreflang="zh">
    24. 

  24.         
    25. 

  25.           <link rel="alternate" href="/ja/" hreflang="ja">
    26. 

  26.         
    27. 

  27.           <link rel="alternate" href="/pt/" hreflang="pt">
    28. 

  28.         
    29. 

  29.           <link rel="alternate" href="/ko/" hreflang="ko">
    30. 

  30.         
    31. 

  31.           <link rel="alternate" href="/ar/" hreflang="ar">
    32. 

  32.         
    33. 

  33.       
    34. 

  34.       
    35. 

  35.       <link rel="icon" href="assets/logo.svg">
    36. 

  36.       <meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.1">
    37. 

  37.     
    38. 

  38.     
    39. 

  39.       
    40. 

  40.         <title>Fish Audio</title>
    41. 

  41.       
    42. 

  42.     
    43. 

  43.     
    44. 

  44.       <link rel="stylesheet" href="assets/stylesheets/main.484c7ddc.min.css">
    45. 

  45.       
    46. 

  46.         
    47. 

  47.         <link rel="stylesheet" href="assets/stylesheets/palette.ab4e12ef.min.css">
    48. 

  48.       
    49. 

  49.       
    50. 

  50. 

  51. 

  52.     
    53. 

  53.     
    54. 

  54.       
    55. 

  55.     
    56. 

  56.     
    57. 

  57.       
    58. 

  58.         
    59. 

  59.         
    60. 

  60.         <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
    61. 

  61.         <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
    62. 

  62.         <style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
    63. 

  63.       
    64. 

  64.     
    65. 

  65.     
    66. 

  66.       <link rel="stylesheet" href="stylesheets/extra.css">
    67. 

  67.     
    68. 

  68.     <script>__md_scope=new URL(".",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
    69. 

  69.     
    70. 

  70.       
    71. 

  71. 

  72.     
    73. 

  73.     
    74. 

  74.   </head>
    75. 

  75.   
    76. 

  76.   
    77. 

  77.     
    78. 

  78.     
    79. 

  79.       
    80. 

  80.     
    81. 

  81.     
    82. 

  82.     
    83. 

  83.     
    84. 

  84.     <body dir="ltr" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo">
    85. 

  85.   
    86. 

  86.     
    87. 

  87.     <input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
    88. 

  88.     <input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
    89. 

  89.     <label class="md-overlay" for="__drawer"></label>
    90. 

  90.     <div data-md-component="skip">
    91. 

  91.       
    92. 

  92.         
    93. 

  93.         <a href="#quick-start" class="md-skip">
    94. 

  94.           Skip to content
    95. 

  95.         </a>
    96. 

  96.       
    97. 

  97.     </div>
    98. 

  98.     <div data-md-component="announce">
    99. 

  99.       
    100. 

  100.     </div>
    101. 

  101.     
    102. 

  102.     
    103. 

  103.       
    104. 

  104. 

  105.   
    106. 

  106. 

  107. <header class="md-header md-header--shadow" data-md-component="header">
    108. 

  108.   <nav class="md-header__inner md-grid" aria-label="Header">
    109. 

  109.     <a href="https://speech.fish.audio" title="Fish Audio" class="md-header__button md-logo" aria-label="Fish Audio" data-md-component="logo">
    110. 

  110.       
    111. 

  111.   <img src="assets/logo.svg" alt="logo">
    112. 

  112. 

  113.     </a>
    114. 

  114.     <label class="md-header__button md-icon" for="__drawer">
    115. 

  115.       
    116. 

  116.       <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
    117. 

  117.     </label>
    118. 

  118.     <div class="md-header__title" data-md-component="header-title">
    119. 

  119.       <div class="md-header__ellipsis">
    120. 

  120.         <div class="md-header__topic">
    121. 

  121.           <span class="md-ellipsis">
    122. 

  122.             Fish Audio
    123. 

  123.           </span>
    124. 

  124.         </div>
    125. 

  125.         <div class="md-header__topic" data-md-component="header-topic">
    126. 

  126.           <span class="md-ellipsis">
    127. 

  127.             
    128. 

  128.               Introduction
    129. 

  129.             
    130. 

  130.           </span>
    131. 

  131.         </div>
    132. 

  132.       </div>
    133. 

  133.     </div>
    134. 

  134.     
    135. 

  135.       
    136. 

  136.         <form class="md-header__option" data-md-component="palette">
    137. 

  137.   
    138. 

  138.     
    139. 

  139.     
    140. 

  140.     
    141. 

  141.     <input class="md-option" data-md-color-media="(prefers-color-scheme)" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo"  aria-label="Switch to light mode"  type="radio" name="__palette" id="__palette_0">
    142. 

  142.     
    143. 

  143.       <label class="md-header__button md-icon" title="Switch to light mode" for="__palette_1" hidden>
    144. 

  144.         <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m14.3 16-.7-2h-3.2l-.7 2H7.8L11 7h2l3.2 9zM20 8.69V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12zm-9.15 3.96h2.3L12 9z"/></svg>
    145. 

  145.       </label>
    146. 

  146.     
    147. 

  147.   
    148. 

  148.     
    149. 

  149.     
    150. 

  150.     
    151. 

  151.     <input class="md-option" data-md-color-media="(prefers-color-scheme: light)" data-md-color-scheme="default" data-md-color-primary="black" data-md-color-accent="indigo"  aria-label="Switch to dark mode"  type="radio" name="__palette" id="__palette_1">
    152. 

  152.     
    153. 

  153.       <label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_2" hidden>
    154. 

  154.         <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a4 4 0 0 0-4 4 4 4 0 0 0 4 4 4 4 0 0 0 4-4 4 4 0 0 0-4-4m0 10a6 6 0 0 1-6-6 6 6 0 0 1 6-6 6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
    155. 

  155.       </label>
    156. 

  156.     
    157. 

  157.   
    158. 

  158.     
    159. 

  159.     
    160. 

  160.     
    161. 

  161.     <input class="md-option" data-md-color-media="(prefers-color-scheme: dark)" data-md-color-scheme="slate" data-md-color-primary="black" data-md-color-accent="indigo"  aria-label="Switch to light mode"  type="radio" name="__palette" id="__palette_2">
    162. 

  162.     
    163. 

  163.       <label class="md-header__button md-icon" title="Switch to light mode" for="__palette_0" hidden>
    164. 

  164.         <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 18c-.89 0-1.74-.2-2.5-.55C11.56 16.5 13 14.42 13 12s-1.44-4.5-3.5-5.45C10.26 6.2 11.11 6 12 6a6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
    165. 

  165.       </label>
    166. 

  166.     
    167. 

  167.   
    168. 

  168. </form>
    169. 

  169.       
    170. 

  170.     
    171. 

  171.     
    172. 

  172.       <script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
    173. 

  173.     
    174. 

  174.     
    175. 

  175.       <div class="md-header__option">
    176. 

  176.   <div class="md-select">
    177. 

  177.     
    178. 

  178.     <button class="md-header__button md-icon" aria-label="Select language">
    179. 

  179.       <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m12.87 15.07-2.54-2.51.03-.03A17.5 17.5 0 0 0 14.07 6H17V4h-7V2H8v2H1v2h11.17C11.5 7.92 10.44 9.75 9 11.35 8.07 10.32 7.3 9.19 6.69 8h-2c.73 1.63 1.73 3.17 2.98 4.56l-5.09 5.02L4 19l5-5 3.11 3.11zM18.5 10h-2L12 22h2l1.12-3h4.75L21 22h2zm-2.62 7 1.62-4.33L19.12 17z"/></svg>
    180. 

  180.     </button>
    181. 

  181.     <div class="md-select__inner">
    182. 

  182.       <ul class="md-select__list">
    183. 

  183.         
    184. 

  184.           <li class="md-select__item">
    185. 

  185.             <a href="/" hreflang="en" class="md-select__link">
    186. 

  186.               English
    187. 

  187.             </a>
    188. 

  188.           </li>
    189. 

  189.         
    190. 

  190.           <li class="md-select__item">
    191. 

  191.             <a href="/zh/" hreflang="zh" class="md-select__link">
    192. 

  192.               简体中文
    193. 

  193.             </a>
    194. 

  194.           </li>
    195. 

  195.         
    196. 

  196.           <li class="md-select__item">
    197. 

  197.             <a href="/ja/" hreflang="ja" class="md-select__link">
    198. 

  198.               日本語
    199. 

  199.             </a>
    200. 

  200.           </li>
    201. 

  201.         
    202. 

  202.           <li class="md-select__item">
    203. 

  203.             <a href="/pt/" hreflang="pt" class="md-select__link">
    204. 

  204.               Português (Brasil)
    205. 

  205.             </a>
    206. 

  206.           </li>
    207. 

  207.         
    208. 

  208.           <li class="md-select__item">
    209. 

  209.             <a href="/ko/" hreflang="ko" class="md-select__link">
    210. 

  210.               한국어
    211. 

  211.             </a>
    212. 

  212.           </li>
    213. 

  213.         
    214. 

  214.           <li class="md-select__item">
    215. 

  215.             <a href="/ar/" hreflang="ar" class="md-select__link">
    216. 

  216.               العربية
    217. 

  217.             </a>
    218. 

  218.           </li>
    219. 

  219.         
    220. 

  220.       </ul>
    221. 

  221.     </div>
    222. 

  222.   </div>
    223. 

  223. </div>
    224. 

  224.     
    225. 

  225.     
    226. 

  226.       
    227. 

  227.       
    228. 

  228.         <label class="md-header__button md-icon" for="__search">
    229. 

  229.           
    230. 

  230.           <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
    231. 

  231.         </label>
    232. 

  232.         <div class="md-search" data-md-component="search" role="dialog">
    233. 

  233.   <label class="md-search__overlay" for="__search"></label>
    234. 

  234.   <div class="md-search__inner" role="search">
    235. 

  235.     <form class="md-search__form" name="search">
    236. 

  236.       <input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
    237. 

  237.       <label class="md-search__icon md-icon" for="__search">
    238. 

  238.         
    239. 

  239.         <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
    240. 

  240.         
    241. 

  241.         <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
    242. 

  242.       </label>
    243. 

  243.       <nav class="md-search__options" aria-label="Search">
    244. 

  244.         
    245. 

  245.           <a href="javascript:void(0)" class="md-search__icon md-icon" title="Share" aria-label="Share" data-clipboard data-clipboard-text="" data-md-component="search-share" tabindex="-1">
    246. 

  246.             
    247. 

  247.             <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M18 16.08c-.76 0-1.44.3-1.96.77L8.91 12.7c.05-.23.09-.46.09-.7s-.04-.47-.09-.7l7.05-4.11c.54.5 1.25.81 2.04.81a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3c0 .24.04.47.09.7L8.04 9.81C7.5 9.31 6.79 9 6 9a3 3 0 0 0-3 3 3 3 0 0 0 3 3c.79 0 1.5-.31 2.04-.81l7.12 4.15c-.05.21-.08.43-.08.66 0 1.61 1.31 2.91 2.92 2.91s2.92-1.3 2.92-2.91A2.92 2.92 0 0 0 18 16.08"/></svg>
    248. 

  248.           </a>
    249. 

  249.         
    250. 

  250.         <button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
    251. 

  251.           
    252. 

  252.           <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
    253. 

  253.         </button>
    254. 

  254.       </nav>
    255. 

  255.       
    256. 

  256.         <div class="md-search__suggest" data-md-component="search-suggest"></div>
    257. 

  257.       
    258. 

  258.     </form>
    259. 

  259.     <div class="md-search__output">
    260. 

  260.       <div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
    261. 

  261.         <div class="md-search-result" data-md-component="search-result">
    262. 

  262.           <div class="md-search-result__meta">
    263. 

  263.             Initializing search
    264. 

  264.           </div>
    265. 

  265.           <ol class="md-search-result__list" role="presentation"></ol>
    266. 

  266.         </div>
    267. 

  267.       </div>
    268. 

  268.     </div>
    269. 

  269.   </div>
    270. 

  270. </div>
    271. 

  271.       
    272. 

  272.     
    273. 

  273.     
    274. 

  274.       <div class="md-header__source">
    275. 

  275.         <a href="https://github.com/fishaudio/fish-speech" title="Go to repository" class="md-source" data-md-component="source">
    276. 

  276.   <div class="md-source__icon md-icon">
    277. 

  277.     
    278. 

  278.     <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M439.6 236.1 244 40.5c-5.4-5.5-12.8-8.5-20.4-8.5s-15 3-20.4 8.4L162.5 81l51.5 51.5c27.1-9.1 52.7 16.8 43.4 43.7l49.7 49.7c34.2-11.8 61.2 31 35.5 56.7-26.5 26.5-70.2-2.9-56-37.3L240.3 199v121.9c25.3 12.5 22.3 41.8 9.1 55-6.4 6.4-15.2 10.1-24.3 10.1s-17.8-3.6-24.3-10.1c-17.6-17.6-11.1-46.9 11.2-56v-123c-20.8-8.5-24.6-30.7-18.6-45L142.6 101 8.5 235.1C3 240.6 0 247.9 0 255.5s3 15 8.5 20.4l195.6 195.7c5.4 5.4 12.7 8.4 20.4 8.4s15-3 20.4-8.4l194.7-194.7c5.4-5.4 8.4-12.8 8.4-20.4s-3-15-8.4-20.4"/></svg>
    279. 

  279.   </div>
    280. 

  280.   <div class="md-source__repository">
    281. 

  281.     fishaudio/fish-speech
    282. 

  282.   </div>
    283. 

  283. </a>
    284. 

  284.       </div>
    285. 

  285.     
    286. 

  286.   </nav>
    287. 

  287.   
    288. 

  288. </header>
    289. 

  289.     
    290. 

  290.     <div class="md-container" data-md-component="container">
    291. 

  291.       
    292. 

  292.       
    293. 

  293.         
    294. 

  294.           
    295. 

  295.         
    296. 

  296.       
    297. 

  297.       <main class="md-main" data-md-component="main">
    298. 

  298.         <div class="md-main__inner md-grid">
    299. 

  299.           
    300. 

  300.             
    301. 

  301.               
    302. 

  302.               <div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
    303. 

  303.                 <div class="md-sidebar__scrollwrap">
    304. 

  304.                   <div class="md-sidebar__inner">
    305. 

  305.                     
    306. 

  306. 

  307. 

  308. 

  309. <nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
    310. 

  310.   <label class="md-nav__title" for="__drawer">
    311. 

  311.     <a href="https://speech.fish.audio" title="Fish Audio" class="md-nav__button md-logo" aria-label="Fish Audio" data-md-component="logo">
    312. 

  312.       
    313. 

  313.   <img src="assets/logo.svg" alt="logo">
    314. 

  314. 

  315.     </a>
    316. 

  316.     Fish Audio
    317. 

  317.   </label>
    318. 

  318.   
    319. 

  319.     <div class="md-nav__source">
    320. 

  320.       <a href="https://github.com/fishaudio/fish-speech" title="Go to repository" class="md-source" data-md-component="source">
    321. 

  321.   <div class="md-source__icon md-icon">
    322. 

  322.     
    323. 

  323.     <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M439.6 236.1 244 40.5c-5.4-5.5-12.8-8.5-20.4-8.5s-15 3-20.4 8.4L162.5 81l51.5 51.5c27.1-9.1 52.7 16.8 43.4 43.7l49.7 49.7c34.2-11.8 61.2 31 35.5 56.7-26.5 26.5-70.2-2.9-56-37.3L240.3 199v121.9c25.3 12.5 22.3 41.8 9.1 55-6.4 6.4-15.2 10.1-24.3 10.1s-17.8-3.6-24.3-10.1c-17.6-17.6-11.1-46.9 11.2-56v-123c-20.8-8.5-24.6-30.7-18.6-45L142.6 101 8.5 235.1C3 240.6 0 247.9 0 255.5s3 15 8.5 20.4l195.6 195.7c5.4 5.4 12.7 8.4 20.4 8.4s15-3 20.4-8.4l194.7-194.7c5.4-5.4 8.4-12.8 8.4-20.4s-3-15-8.4-20.4"/></svg>
    324. 

  324.   </div>
    325. 

  325.   <div class="md-source__repository">
    326. 

  326.     fishaudio/fish-speech
    327. 

  327.   </div>
    328. 

  328. </a>
    329. 

  329.     </div>
    330. 

  330.   
    331. 

  331.   <ul class="md-nav__list" data-md-scrollfix>
    332. 

  332.     
    333. 

  333.       
    334. 

  334.       
    335. 

  335.   
    336. 

  336.   
    337. 

  337.     
    338. 

  338.   
    339. 

  339.   
    340. 

  340.   
    341. 

  341.     <li class="md-nav__item md-nav__item--active">
    342. 

  342.       
    343. 

  343.       <input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
    344. 

  344.       
    345. 

  345.       
    346. 

  346.       
    347. 

  347.         <label class="md-nav__link md-nav__link--active" for="__toc">
    348. 

  348.           
    349. 

  349.   
    350. 

  350.   
    351. 

  351.   <span class="md-ellipsis">
    352. 

  352.     
    353. 

  353.   
    354. 

  354.     Introduction
    355. 

  355.   
    356. 

  356. 

  357.     
    358. 

  358.   </span>
    359. 

  359.   
    360. 

  360.   
    361. 

  361. 

  362.           <span class="md-nav__icon md-icon"></span>
    363. 

  363.         </label>
    364. 

  364.       
    365. 

  365.       <a href="." class="md-nav__link md-nav__link--active">
    366. 

  366.         
    367. 

  367.   
    368. 

  368.   
    369. 

  369.   <span class="md-ellipsis">
    370. 

  370.     
    371. 

  371.   
    372. 

  372.     Introduction
    373. 

  373.   
    374. 

  374. 

  375.     
    376. 

  376.   </span>
    377. 

  377.   
    378. 

  378.   
    379. 

  379. 

  380.       </a>
    381. 

  381.       
    382. 

  382.         
    383. 

  383. 

  384. <nav class="md-nav md-nav--secondary" aria-label="Table of contents">
    385. 

  385.   
    386. 

  386.   
    387. 

  387.   
    388. 

  388.   
    389. 

  389.     <label class="md-nav__title" for="__toc">
    390. 

  390.       <span class="md-nav__icon md-icon"></span>
    391. 

  391.       Table of contents
    392. 

  392.     </label>
    393. 

  393.     <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
    394. 

  394.       
    395. 

  395.         <li class="md-nav__item">
    396. 

  396.   <a href="#quick-start" class="md-nav__link">
    397. 

  397.     <span class="md-ellipsis">
    398. 

  398.       
    399. 

  399.         Quick Start
    400. 

  400.       
    401. 

  401.     </span>
    402. 

  402.   </a>
    403. 

  403.   
    404. 

  404.     <nav class="md-nav" aria-label="Quick Start">
    405. 

  405.       <ul class="md-nav__list">
    406. 

  406.         
    407. 

  407.           <li class="md-nav__item">
    408. 

  408.   <a href="#for-human" class="md-nav__link">
    409. 

  409.     <span class="md-ellipsis">
    410. 

  410.       
    411. 

  411.         For Human
    412. 

  412.       
    413. 

  413.     </span>
    414. 

  414.   </a>
    415. 

  415.   
    416. 

  416. </li>
    417. 

  417.         
    418. 

  418.           <li class="md-nav__item">
    419. 

  419.   <a href="#for-llm-agent" class="md-nav__link">
    420. 

  420.     <span class="md-ellipsis">
    421. 

  421.       
    422. 

  422.         For LLM Agent
    423. 

  423.       
    424. 

  424.     </span>
    425. 

  425.   </a>
    426. 

  426.   
    427. 

  427. </li>
    428. 

  428.         
    429. 

  429.       </ul>
    430. 

  430.     </nav>
    431. 

  431.   
    432. 

  432. </li>
    433. 

  433.       
    434. 

  434.         <li class="md-nav__item">
    435. 

  435.   <a href="#fish-audio-s2" class="md-nav__link">
    436. 

  436.     <span class="md-ellipsis">
    437. 

  437.       
    438. 

  438.         Fish Audio S2
    439. 

  439.       
    440. 

  440.     </span>
    441. 

  441.   </a>
    442. 

  442.   
    443. 

  443.     <nav class="md-nav" aria-label="Fish Audio S2">
    444. 

  444.       <ul class="md-nav__list">
    445. 

  445.         
    446. 

  446.           <li class="md-nav__item">
    447. 

  447.   <a href="#model-variants" class="md-nav__link">
    448. 

  448.     <span class="md-ellipsis">
    449. 

  449.       
    450. 

  450.         Model Variants
    451. 

  451.       
    452. 

  452.     </span>
    453. 

  453.   </a>
    454. 

  454.   
    455. 

  455. </li>
    456. 

  456.         
    457. 

  457.       </ul>
    458. 

  458.     </nav>
    459. 

  459.   
    460. 

  460. </li>
    461. 

  461.       
    462. 

  462.         <li class="md-nav__item">
    463. 

  463.   <a href="#benchmark-results" class="md-nav__link">
    464. 

  464.     <span class="md-ellipsis">
    465. 

  465.       
    466. 

  466.         Benchmark Results
    467. 

  467.       
    468. 

  468.     </span>
    469. 

  469.   </a>
    470. 

  470.   
    471. 

  471. </li>
    472. 

  472.       
    473. 

  473.         <li class="md-nav__item">
    474. 

  474.   <a href="#highlights" class="md-nav__link">
    475. 

  475.     <span class="md-ellipsis">
    476. 

  476.       
    477. 

  477.         Highlights
    478. 

  478.       
    479. 

  479.     </span>
    480. 

  480.   </a>
    481. 

  481.   
    482. 

  482.     <nav class="md-nav" aria-label="Highlights">
    483. 

  483.       <ul class="md-nav__list">
    484. 

  484.         
    485. 

  485.           <li class="md-nav__item">
    486. 

  486.   <a href="#fine-grained-inline-control-via-natural-language" class="md-nav__link">
    487. 

  487.     <span class="md-ellipsis">
    488. 

  488.       
    489. 

  489.         Fine-Grained Inline Control via Natural Language
    490. 

  490.       
    491. 

  491.     </span>
    492. 

  492.   </a>
    493. 

  493.   
    494. 

  494. </li>
    495. 

  495.         
    496. 

  496.           <li class="md-nav__item">
    497. 

  497.   <a href="#dual-autoregressive-architecture" class="md-nav__link">
    498. 

  498.     <span class="md-ellipsis">
    499. 

  499.       
    500. 

  500.         Dual-Autoregressive Architecture
    501. 

  501.       
    502. 

  502.     </span>
    503. 

  503.   </a>
    504. 

  504.   
    505. 

  505. </li>
    506. 

  506.         
    507. 

  507.           <li class="md-nav__item">
    508. 

  508.   <a href="#reinforcement-learning-alignment" class="md-nav__link">
    509. 

  509.     <span class="md-ellipsis">
    510. 

  510.       
    511. 

  511.         Reinforcement Learning Alignment
    512. 

  512.       
    513. 

  513.     </span>
    514. 

  514.   </a>
    515. 

  515.   
    516. 

  516. </li>
    517. 

  517.         
    518. 

  518.           <li class="md-nav__item">
    519. 

  519.   <a href="#production-streaming-via-sglang" class="md-nav__link">
    520. 

  520.     <span class="md-ellipsis">
    521. 

  521.       
    522. 

  522.         Production Streaming via SGLang
    523. 

  523.       
    524. 

  524.     </span>
    525. 

  525.   </a>
    526. 

  526.   
    527. 

  527. </li>
    528. 

  528.         
    529. 

  529.           <li class="md-nav__item">
    530. 

  530.   <a href="#multilingual-support" class="md-nav__link">
    531. 

  531.     <span class="md-ellipsis">
    532. 

  532.       
    533. 

  533.         Multilingual Support
    534. 

  534.       
    535. 

  535.     </span>
    536. 

  536.   </a>
    537. 

  537.   
    538. 

  538. </li>
    539. 

  539.         
    540. 

  540.           <li class="md-nav__item">
    541. 

  541.   <a href="#native-multi-speaker-generation" class="md-nav__link">
    542. 

  542.     <span class="md-ellipsis">
    543. 

  543.       
    544. 

  544.         Native Multi-Speaker Generation
    545. 

  545.       
    546. 

  546.     </span>
    547. 

  547.   </a>
    548. 

  548.   
    549. 

  549. </li>
    550. 

  550.         
    551. 

  551.           <li class="md-nav__item">
    552. 

  552.   <a href="#multi-turn-generation" class="md-nav__link">
    553. 

  553.     <span class="md-ellipsis">
    554. 

  554.       
    555. 

  555.         Multi-Turn Generation
    556. 

  556.       
    557. 

  557.     </span>
    558. 

  558.   </a>
    559. 

  559.   
    560. 

  560. </li>
    561. 

  561.         
    562. 

  562.           <li class="md-nav__item">
    563. 

  563.   <a href="#rapid-voice-cloning" class="md-nav__link">
    564. 

  564.     <span class="md-ellipsis">
    565. 

  565.       
    566. 

  566.         Rapid Voice Cloning
    567. 

  567.       
    568. 

  568.     </span>
    569. 

  569.   </a>
    570. 

  570.   
    571. 

  571. </li>
    572. 

  572.         
    573. 

  573.       </ul>
    574. 

  574.     </nav>
    575. 

  575.   
    576. 

  576. </li>
    577. 

  577.       
    578. 

  578.         <li class="md-nav__item">
    579. 

  579.   <a href="#credits" class="md-nav__link">
    580. 

  580.     <span class="md-ellipsis">
    581. 

  581.       
    582. 

  582.         Credits
    583. 

  583.       
    584. 

  584.     </span>
    585. 

  585.   </a>
    586. 

  586.   
    587. 

  587. </li>
    588. 

  588.       
    589. 

  589.         <li class="md-nav__item">
    590. 

  590.   <a href="#tech-report" class="md-nav__link">
    591. 

  591.     <span class="md-ellipsis">
    592. 

  592.       
    593. 

  593.         Tech Report
    594. 

  594.       
    595. 

  595.     </span>
    596. 

  596.   </a>
    597. 

  597.   
    598. 

  598. </li>
    599. 

  599.       
    600. 

  600.     </ul>
    601. 

  601.   
    602. 

  602. </nav>
    603. 

  603.       
    604. 

  604.     </li>
    605. 

  605.   
    606. 

  606. 

  607.     
    608. 

  608.       
    609. 

  609.       
    610. 

  610.   
    611. 

  611.   
    612. 

  612.   
    613. 

  613.   
    614. 

  614.     <li class="md-nav__item">
    615. 

  615.       <a href="install/" class="md-nav__link">
    616. 

  616.         
    617. 

  617.   
    618. 

  618.   
    619. 

  619.   <span class="md-ellipsis">
    620. 

  620.     
    621. 

  621.   
    622. 

  622.     Installation
    623. 

  623.   
    624. 

  624. 

  625.     
    626. 

  626.   </span>
    627. 

  627.   
    628. 

  628.   
    629. 

  629. 

  630.       </a>
    631. 

  631.     </li>
    632. 

  632.   
    633. 

  633. 

  634.     
    635. 

  635.       
    636. 

  636.       
    637. 

  637.   
    638. 

  638.   
    639. 

  639.   
    640. 

  640.   
    641. 

  641.     <li class="md-nav__item">
    642. 

  642.       <a href="finetune/" class="md-nav__link">
    643. 

  643.         
    644. 

  644.   
    645. 

  645.   
    646. 

  646.   <span class="md-ellipsis">
    647. 

  647.     
    648. 

  648.   
    649. 

  649.     Finetune
    650. 

  650.   
    651. 

  651. 

  652.     
    653. 

  653.   </span>
    654. 

  654.   
    655. 

  655.   
    656. 

  656. 

  657.       </a>
    658. 

  658.     </li>
    659. 

  659.   
    660. 

  660. 

  661.     
    662. 

  662.       
    663. 

  663.       
    664. 

  664.   
    665. 

  665.   
    666. 

  666.   
    667. 

  667.   
    668. 

  668.     <li class="md-nav__item">
    669. 

  669.       <a href="inference/" class="md-nav__link">
    670. 

  670.         
    671. 

  671.   
    672. 

  672.   
    673. 

  673.   <span class="md-ellipsis">
    674. 

  674.     
    675. 

  675.   
    676. 

  676.     Inference
    677. 

  677.   
    678. 

  678. 

  679.     
    680. 

  680.   </span>
    681. 

  681.   
    682. 

  682.   
    683. 

  683. 

  684.       </a>
    685. 

  685.     </li>
    686. 

  686.   
    687. 

  687. 

  688.     
    689. 

  689.       
    690. 

  690.       
    691. 

  691.   
    692. 

  692.   
    693. 

  693.   
    694. 

  694.   
    695. 

  695.     <li class="md-nav__item">
    696. 

  696.       <a href="server/" class="md-nav__link">
    697. 

  697.         
    698. 

  698.   
    699. 

  699.   
    700. 

  700.   <span class="md-ellipsis">
    701. 

  701.     
    702. 

  702.   
    703. 

  703.     Server
    704. 

  704.   
    705. 

  705. 

  706.     
    707. 

  707.   </span>
    708. 

  708.   
    709. 

  709.   
    710. 

  710. 

  711.       </a>
    712. 

  712.     </li>
    713. 

  713.   
    714. 

  714. 

  715.     
    716. 

  716.       
    717. 

  717.       
    718. 

  718.   
    719. 

  719.   
    720. 

  720.   
    721. 

  721.   
    722. 

  722.     <li class="md-nav__item">
    723. 

  723.       <a href="en/samples.md" class="md-nav__link">
    724. 

  724.         
    725. 

  725.   
    726. 

  726.   
    727. 

  727.   <span class="md-ellipsis">
    728. 

  728.     
    729. 

  729.   
    730. 

  730.     Samples
    731. 

  731.   
    732. 

  732. 

  733.     
    734. 

  734.   </span>
    735. 

  735.   
    736. 

  736.   
    737. 

  737. 

  738.       </a>
    739. 

  739.     </li>
    740. 

  740.   
    741. 

  741. 

  742.     
    743. 

  743.   </ul>
    744. 

  744. </nav>
    745. 

  745.                   </div>
    746. 

  746.                 </div>
    747. 

  747.               </div>
    748. 

  748.             
    749. 

  749.             
    750. 

  750.               
    751. 

  751.               <div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
    752. 

  752.                 <div class="md-sidebar__scrollwrap">
    753. 

  753.                   <div class="md-sidebar__inner">
    754. 

  754.                     
    755. 

  755. 

  756. <nav class="md-nav md-nav--secondary" aria-label="Table of contents">
    757. 

  757.   
    758. 

  758.   
    759. 

  759.   
    760. 

  760.   
    761. 

  761.     <label class="md-nav__title" for="__toc">
    762. 

  762.       <span class="md-nav__icon md-icon"></span>
    763. 

  763.       Table of contents
    764. 

  764.     </label>
    765. 

  765.     <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
    766. 

  766.       
    767. 

  767.         <li class="md-nav__item">
    768. 

  768.   <a href="#quick-start" class="md-nav__link">
    769. 

  769.     <span class="md-ellipsis">
    770. 

  770.       
    771. 

  771.         Quick Start
    772. 

  772.       
    773. 

  773.     </span>
    774. 

  774.   </a>
    775. 

  775.   
    776. 

  776.     <nav class="md-nav" aria-label="Quick Start">
    777. 

  777.       <ul class="md-nav__list">
    778. 

  778.         
    779. 

  779.           <li class="md-nav__item">
    780. 

  780.   <a href="#for-human" class="md-nav__link">
    781. 

  781.     <span class="md-ellipsis">
    782. 

  782.       
    783. 

  783.         For Human
    784. 

  784.       
    785. 

  785.     </span>
    786. 

  786.   </a>
    787. 

  787.   
    788. 

  788. </li>
    789. 

  789.         
    790. 

  790.           <li class="md-nav__item">
    791. 

  791.   <a href="#for-llm-agent" class="md-nav__link">
    792. 

  792.     <span class="md-ellipsis">
    793. 

  793.       
    794. 

  794.         For LLM Agent
    795. 

  795.       
    796. 

  796.     </span>
    797. 

  797.   </a>
    798. 

  798.   
    799. 

  799. </li>
    800. 

  800.         
    801. 

  801.       </ul>
    802. 

  802.     </nav>
    803. 

  803.   
    804. 

  804. </li>
    805. 

  805.       
    806. 

  806.         <li class="md-nav__item">
    807. 

  807.   <a href="#fish-audio-s2" class="md-nav__link">
    808. 

  808.     <span class="md-ellipsis">
    809. 

  809.       
    810. 

  810.         Fish Audio S2
    811. 

  811.       
    812. 

  812.     </span>
    813. 

  813.   </a>
    814. 

  814.   
    815. 

  815.     <nav class="md-nav" aria-label="Fish Audio S2">
    816. 

  816.       <ul class="md-nav__list">
    817. 

  817.         
    818. 

  818.           <li class="md-nav__item">
    819. 

  819.   <a href="#model-variants" class="md-nav__link">
    820. 

  820.     <span class="md-ellipsis">
    821. 

  821.       
    822. 

  822.         Model Variants
    823. 

  823.       
    824. 

  824.     </span>
    825. 

  825.   </a>
    826. 

  826.   
    827. 

  827. </li>
    828. 

  828.         
    829. 

  829.       </ul>
    830. 

  830.     </nav>
    831. 

  831.   
    832. 

  832. </li>
    833. 

  833.       
    834. 

  834.         <li class="md-nav__item">
    835. 

  835.   <a href="#benchmark-results" class="md-nav__link">
    836. 

  836.     <span class="md-ellipsis">
    837. 

  837.       
    838. 

  838.         Benchmark Results
    839. 

  839.       
    840. 

  840.     </span>
    841. 

  841.   </a>
    842. 

  842.   
    843. 

  843. </li>
    844. 

  844.       
    845. 

  845.         <li class="md-nav__item">
    846. 

  846.   <a href="#highlights" class="md-nav__link">
    847. 

  847.     <span class="md-ellipsis">
    848. 

  848.       
    849. 

  849.         Highlights
    850. 

  850.       
    851. 

  851.     </span>
    852. 

  852.   </a>
    853. 

  853.   
    854. 

  854.     <nav class="md-nav" aria-label="Highlights">
    855. 

  855.       <ul class="md-nav__list">
    856. 

  856.         
    857. 

  857.           <li class="md-nav__item">
    858. 

  858.   <a href="#fine-grained-inline-control-via-natural-language" class="md-nav__link">
    859. 

  859.     <span class="md-ellipsis">
    860. 

  860.       
    861. 

  861.         Fine-Grained Inline Control via Natural Language
    862. 

  862.       
    863. 

  863.     </span>
    864. 

  864.   </a>
    865. 

  865.   
    866. 

  866. </li>
    867. 

  867.         
    868. 

  868.           <li class="md-nav__item">
    869. 

  869.   <a href="#dual-autoregressive-architecture" class="md-nav__link">
    870. 

  870.     <span class="md-ellipsis">
    871. 

  871.       
    872. 

  872.         Dual-Autoregressive Architecture
    873. 

  873.       
    874. 

  874.     </span>
    875. 

  875.   </a>
    876. 

  876.   
    877. 

  877. </li>
    878. 

  878.         
    879. 

  879.           <li class="md-nav__item">
    880. 

  880.   <a href="#reinforcement-learning-alignment" class="md-nav__link">
    881. 

  881.     <span class="md-ellipsis">
    882. 

  882.       
    883. 

  883.         Reinforcement Learning Alignment
    884. 

  884.       
    885. 

  885.     </span>
    886. 

  886.   </a>
    887. 

  887.   
    888. 

  888. </li>
    889. 

  889.         
    890. 

  890.           <li class="md-nav__item">
    891. 

  891.   <a href="#production-streaming-via-sglang" class="md-nav__link">
    892. 

  892.     <span class="md-ellipsis">
    893. 

  893.       
    894. 

  894.         Production Streaming via SGLang
    895. 

  895.       
    896. 

  896.     </span>
    897. 

  897.   </a>
    898. 

  898.   
    899. 

  899. </li>
    900. 

  900.         
    901. 

  901.           <li class="md-nav__item">
    902. 

  902.   <a href="#multilingual-support" class="md-nav__link">
    903. 

  903.     <span class="md-ellipsis">
    904. 

  904.       
    905. 

  905.         Multilingual Support
    906. 

  906.       
    907. 

  907.     </span>
    908. 

  908.   </a>
    909. 

  909.   
    910. 

  910. </li>
    911. 

  911.         
    912. 

  912.           <li class="md-nav__item">
    913. 

  913.   <a href="#native-multi-speaker-generation" class="md-nav__link">
    914. 

  914.     <span class="md-ellipsis">
    915. 

  915.       
    916. 

  916.         Native Multi-Speaker Generation
    917. 

  917.       
    918. 

  918.     </span>
    919. 

  919.   </a>
    920. 

  920.   
    921. 

  921. </li>
    922. 

  922.         
    923. 

  923.           <li class="md-nav__item">
    924. 

  924.   <a href="#multi-turn-generation" class="md-nav__link">
    925. 

  925.     <span class="md-ellipsis">
    926. 

  926.       
    927. 

  927.         Multi-Turn Generation
    928. 

  928.       
    929. 

  929.     </span>
    930. 

  930.   </a>
    931. 

  931.   
    932. 

  932. </li>
    933. 

  933.         
    934. 

  934.           <li class="md-nav__item">
    935. 

  935.   <a href="#rapid-voice-cloning" class="md-nav__link">
    936. 

  936.     <span class="md-ellipsis">
    937. 

  937.       
    938. 

  938.         Rapid Voice Cloning
    939. 

  939.       
    940. 

  940.     </span>
    941. 

  941.   </a>
    942. 

  942.   
    943. 

  943. </li>
    944. 

  944.         
    945. 

  945.       </ul>
    946. 

  946.     </nav>
    947. 

  947.   
    948. 

  948. </li>
    949. 

  949.       
    950. 

  950.         <li class="md-nav__item">
    951. 

  951.   <a href="#credits" class="md-nav__link">
    952. 

  952.     <span class="md-ellipsis">
    953. 

  953.       
    954. 

  954.         Credits
    955. 

  955.       
    956. 

  956.     </span>
    957. 

  957.   </a>
    958. 

  958.   
    959. 

  959. </li>
    960. 

  960.       
    961. 

  961.         <li class="md-nav__item">
    962. 

  962.   <a href="#tech-report" class="md-nav__link">
    963. 

  963.     <span class="md-ellipsis">
    964. 

  964.       
    965. 

  965.         Tech Report
    966. 

  966.       
    967. 

  967.     </span>
    968. 

  968.   </a>
    969. 

  969.   
    970. 

  970. </li>
    971. 

  971.       
    972. 

  972.     </ul>
    973. 

  973.   
    974. 

  974. </nav>
    975. 

  975.                   </div>
    976. 

  976.                 </div>
    977. 

  977.               </div>
    978. 

  978.             
    979. 

  979.           
    980. 

  980.           
    981. 

  981.             <div class="md-content" data-md-component="content">
    982. 

  982.               
    983. 

  983.               <article class="md-content__inner md-typeset">
    984. 

  984.                 
    985. 

  985.                   
    986. 

  986. 

  987. 

  988.   
    989. 

  989.     <a href="https://github.com/fishaudio/fish-speech/blob/main/docs/en/index.md" title="Edit this page" class="md-content__button md-icon" rel="edit">
    990. 

  990.       
    991. 

  991.       <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M10 20H6V4h7v5h5v3.1l2-2V8l-6-6H6c-1.1 0-2 .9-2 2v16c0 1.1.9 2 2 2h4zm10.2-7c.1 0 .3.1.4.2l1.3 1.3c.2.2.2.6 0 .8l-1 1-2.1-2.1 1-1c.1-.1.2-.2.4-.2m0 3.9L14.1 23H12v-2.1l6.1-6.1z"/></svg>
    992. 

  992.     </a>
    993. 

  993.   
    994. 

  994.   
    995. 

  995.     
    996. 

  996.       
    997. 

  997.     
    998. 

  998.     <a href="https://github.com/fishaudio/fish-speech/raw/main/docs/en/index.md" title="View source of this page" class="md-content__button md-icon">
    999. 

  999.       
    1000. 

  1000.       <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M17 18c.56 0 1 .44 1 1s-.44 1-1 1-1-.44-1-1 .44-1 1-1m0-3c-2.73 0-5.06 1.66-6 4 .94 2.34 3.27 4 6 4s5.06-1.66 6-4c-.94-2.34-3.27-4-6-4m0 6.5a2.5 2.5 0 0 1-2.5-2.5 2.5 2.5 0 0 1 2.5-2.5 2.5 2.5 0 0 1 2.5 2.5 2.5 2.5 0 0 1-2.5 2.5M9.27 20H6V4h7v5h5v4.07c.7.08 1.36.25 2 .49V8l-6-6H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h4.5a8.2 8.2 0 0 1-1.23-2"/></svg>
    1001. 

  1001.     </a>
    1002. 

  1002.   
    1003. 

  1003. 

  1004. 

  1005. <div align="center">
    1006. 

  1006. <h1>Fish Speech</h1>
    1007. 

  1007. 

  1008. <p><strong>English</strong> | <a href="../zh/">简体中文</a> | <a href="../pt/">Portuguese</a> | <a href="../ja/">日本語</a> | <a href="../ko/">한국어</a> | <a href="../ar/">العربية</a> | <a href="../es/">Español</a></p>
    1009. 

  1009. 

  1010. <a href="https://www.producthunt.com/products/fish-speech?embed=true&utm_source=badge-top-post-badge&utm_medium=badge&utm_source=badge-fish&#0045;audio&#0045;s1" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/top-post-badge.svg?post_id=1023740&theme=light&period=daily&t=1761164814710" alt="Fish&#0032;Audio&#0032;S1 - Expressive&#0032;Voice&#0032;Cloning&#0032;and&#0032;Text&#0045;to&#0045;Speech | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
    1011. 

  1011. <a href="https://trendshift.io/repositories/7014" target="_blank">
    1012. 

  1012.     <img src="https://trendshift.io/api/badge/repositories/7014" alt="fishaudio%2Ffish-speech | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>
    1013. 

  1013. </a>
    1014. 

  1014. </div>
    1015. 

  1015. 

  1016. <p><br></p>
    1017. 

  1017. <div align="center">
    1018. 

  1018.     <img src="https://count.getloli.com/get/@fish-speech?theme=asoul" /><br>
    1019. 

  1019. </div>
    1020. 

  1020. 

  1021. <p><br></p>
    1022. 

  1022. <div align="center">
    1023. 

  1023.     <a target="_blank" href="https://discord.gg/Es5qTB9BcN">
    1024. 

  1024.         <img alt="Discord" src="https://img.shields.io/discord/1214047546020728892?color=%23738ADB&label=Discord&logo=discord&logoColor=white&style=flat-square"/>
    1025. 

  1025.     </a>
    1026. 

  1026.     <a target="_blank" href="https://hub.docker.com/r/fishaudio/fish-speech">
    1027. 

  1027.         <img alt="Docker" src="https://img.shields.io/docker/pulls/fishaudio/fish-speech?style=flat-square&logo=docker"/>
    1028. 

  1028.     </a>
    1029. 

  1029.     <a target="_blank" href="https://pd.qq.com/s/bwxia254o">
    1030. 

  1030.       <img alt="QQ Channel" src="https://img.shields.io/badge/QQ-blue?logo=tencentqq">
    1031. 

  1031.     </a>
    1032. 

  1032. </div>
    1033. 

  1033. 

  1034. <div align="center">
    1035. 

  1035.     <a target="_blank" href="https://huggingface.co/fishaudio/s2">
    1036. 

  1036.         <img alt="HuggingFace Model" src="https://img.shields.io/badge/🤗%20-models-orange"/>
    1037. 

  1037.     </a>
    1038. 

  1038.     <a target="_blank" href="https://fish.audio/blog/fish-audio-open-sources-s2/">
    1039. 

  1039.         <img alt="Fish Audio Blog" src="https://img.shields.io/badge/Blog-Fish_Audio_S2-1f7a8c?style=flat-square&logo=readme&logoColor=white"/>
    1040. 

  1040.     </a>
    1041. 

  1041.     <a target="_blank" href="https://arxiv.org/abs/2603.08823">
    1042. 

  1042.         <img alt="Paper | Technical Report" src="https://img.shields.io/badge/Paper-Technical_Report-b31b1b?style=flat-square"/>
    1043. 

  1043.     </a>
    1044. 

  1044. </div>
    1045. 

  1045. 

  1046. <div class="admonition info">
    1047. 

  1047. <p class="admonition-title">License Notice</p>
    1048. 

  1048. <p>This codebase and its associated model weights are released under <strong>FISH AUDIO RESEARCH LICENSE</strong>. Please refer to <a href="https://github.com/fishaudio/fish-speech/blob/main/LICENSE">LICENSE</a> for more details. We will take action against any violation of the license.</p>
    1049. 

  1049. </div>
    1050. 

  1050. <div class="admonition warning">
    1051. 

  1051. <p class="admonition-title">Legal Disclaimer</p>
    1052. 

  1052. <p>We do not hold any responsibility for any illegal usage of the codebase. Please refer to your local laws about DMCA and other related laws.</p>
    1053. 

  1053. </div>
    1054. 

  1054. <h2 id="quick-start">Quick Start</h2>
    1055. 

  1055. <h3 id="for-human">For Human</h3>
    1056. 

  1056. <p>Here are the official documents for Fish Audio S2, follow the instructions to get started easily.</p>
    1057. 

  1057. <ul>
    1058. 

  1058. <li><a href="https://speech.fish.audio/install/">Installation</a></li>
    1059. 

  1059. <li><a href="https://speech.fish.audio/inference/#command-line-inference">Command Line Inference</a></li>
    1060. 

  1060. <li><a href="https://speech.fish.audio/inference/#webui-inference">WebUI Inference</a></li>
    1061. 

  1061. <li><a href="https://speech.fish.audio/server/">Server Inference</a></li>
    1062. 

  1062. <li><a href="https://speech.fish.audio/install/#docker-setup">Docker Setup</a></li>
    1063. 

  1063. </ul>
    1064. 

  1064. <blockquote>
    1065. 

  1065. <p>[!IMPORTANT]
    1066. 

  1066. <strong>For SGLang server, please read <a href="https://github.com/sgl-project/sglang-omni/blob/main/sglang_omni/models/fishaudio_s2_pro/README.md">SGLang-Omni README</a>.</strong></p>
    1067. 

  1067. </blockquote>
    1068. 

  1068. <h3 id="for-llm-agent">For LLM Agent</h3>
    1069. 

  1069. <div class="language-text highlight"><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1" href="#__codelineno-0-1"></a>Install and configure Fish-Audio S2 by following the instructions here: https://speech.fish.audio/install/
    1070. 

  1070. </span></code></pre></div>
    1071. 

  1071. <h2 id="fish-audio-s2">Fish Audio S2</h2>
    1072. 

  1072. <p><strong>Best text-to-speech system among both open source and closed source</strong></p>
    1073. 

  1073. <p>Fish Audio S2 is the latest model developed by <a href="https://fish.audio/">Fish Audio</a>. Trained on over 10 million hours of audio across approximately 50 languages, S2 combines reinforcement learning alignment with a Dual-Autoregressive architecture to generate speech that sounds natural, realistic, and emotionally rich.</p>
    1074. 

  1074. <p>S2 supports fine-grained inline control of prosody and emotion using natural-language tags like <code>[laugh]</code>, <code>[whispers]</code>, and <code>[super happy]</code>, as well as native multi-speaker and multi-turn generation.</p>
    1075. 

  1075. <p>Visit the <a href="https://fish.audio/">Fish Audio website</a> for live playground. Read the <a href="https://fish.audio/blog/fish-audio-open-sources-s2/">blog post</a> and <a href="https://arxiv.org/abs/2603.08823">technical report</a> for more details.</p>
    1076. 

  1076. <h3 id="model-variants">Model Variants</h3>
    1077. 

  1077. <table>
    1078. 

  1078. <thead>
    1079. 

  1079. <tr>
    1080. 

  1080. <th>Model</th>
    1081. 

  1081. <th>Size</th>
    1082. 

  1082. <th>Availability</th>
    1083. 

  1083. <th>Description</th>
    1084. 

  1084. </tr>
    1085. 

  1085. </thead>
    1086. 

  1086. <tbody>
    1087. 

  1087. <tr>
    1088. 

  1088. <td>S2-Pro</td>
    1089. 

  1089. <td>4B parameters</td>
    1090. 

  1090. <td><a href="https://huggingface.co/fishaudio/s2-pro">HuggingFace</a></td>
    1091. 

  1091. <td>Full-featured flagship model with maximum quality and stability</td>
    1092. 

  1092. </tr>
    1093. 

  1093. </tbody>
    1094. 

  1094. </table>
    1095. 

  1095. <p>More details of the model can be found in the <a href="https://arxiv.org/abs/2411.01156">technical report</a>.</p>
    1096. 

  1096. <h2 id="benchmark-results">Benchmark Results</h2>
    1097. 

  1097. <table>
    1098. 

  1098. <thead>
    1099. 

  1099. <tr>
    1100. 

  1100. <th>Benchmark</th>
    1101. 

  1101. <th>Fish Audio S2</th>
    1102. 

  1102. </tr>
    1103. 

  1103. </thead>
    1104. 

  1104. <tbody>
    1105. 

  1105. <tr>
    1106. 

  1106. <td>Seed-TTS Eval — WER (Chinese)</td>
    1107. 

  1107. <td><strong>0.54%</strong> (best overall)</td>
    1108. 

  1108. </tr>
    1109. 

  1109. <tr>
    1110. 

  1110. <td>Seed-TTS Eval — WER (English)</td>
    1111. 

  1111. <td><strong>0.99%</strong> (best overall)</td>
    1112. 

  1112. </tr>
    1113. 

  1113. <tr>
    1114. 

  1114. <td>Audio Turing Test (with instruction)</td>
    1115. 

  1115. <td><strong>0.515</strong> posterior mean</td>
    1116. 

  1116. </tr>
    1117. 

  1117. <tr>
    1118. 

  1118. <td>EmergentTTS-Eval — Win Rate</td>
    1119. 

  1119. <td><strong>81.88%</strong> (highest overall)</td>
    1120. 

  1120. </tr>
    1121. 

  1121. <tr>
    1122. 

  1122. <td>Fish Instruction Benchmark — TAR</td>
    1123. 

  1123. <td><strong>93.3%</strong></td>
    1124. 

  1124. </tr>
    1125. 

  1125. <tr>
    1126. 

  1126. <td>Fish Instruction Benchmark — Quality</td>
    1127. 

  1127. <td><strong>4.51 / 5.0</strong></td>
    1128. 

  1128. </tr>
    1129. 

  1129. <tr>
    1130. 

  1130. <td>Multilingual (MiniMax Testset) — Best WER</td>
    1131. 

  1131. <td><strong>11 of 24</strong> languages</td>
    1132. 

  1132. </tr>
    1133. 

  1133. <tr>
    1134. 

  1134. <td>Multilingual (MiniMax Testset) — Best SIM</td>
    1135. 

  1135. <td><strong>17 of 24</strong> languages</td>
    1136. 

  1136. </tr>
    1137. 

  1137. </tbody>
    1138. 

  1138. </table>
    1139. 

  1139. <p>On Seed-TTS Eval, S2 achieves the lowest WER among all evaluated models including closed-source systems: Qwen3-TTS (0.77/1.24), MiniMax Speech-02 (0.99/1.90), Seed-TTS (1.12/2.25). On the Audio Turing Test, 0.515 surpasses Seed-TTS (0.417) by 24% and MiniMax-Speech (0.387) by 33%. On EmergentTTS-Eval, S2 achieves particularly strong results in paralinguistics (91.61% win rate), questions (84.41%), and syntactic complexity (83.39%).</p>
    1140. 

  1140. <h2 id="highlights">Highlights</h2>
    1141. 

  1141. <p><img src="../assets/totalability.png" width=200%></p>
    1142. 

  1142. <h3 id="fine-grained-inline-control-via-natural-language">Fine-Grained Inline Control via Natural Language</h3>
    1143. 

  1143. <p>S2 enables localized control over speech generation by embedding natural-language instructions directly at specific word or phrase positions within the text. Rather than relying on a fixed set of predefined tags, S2 accepts free-form textual descriptions — such as <code>[whisper in small voice]</code>, <code>[professional broadcast tone]</code>, or <code>[pitch up]</code> — allowing open-ended expression control at the word level.</p>
    1144. 

  1144. <h3 id="dual-autoregressive-architecture">Dual-Autoregressive Architecture</h3>
    1145. 

  1145. <p>S2 builds on a decoder-only transformer combined with an RVQ-based audio codec (10 codebooks, ~21 Hz frame rate). The Dual-AR architecture splits generation into two stages:</p>
    1146. 

  1146. <ul>
    1147. 

  1147. <li><strong>Slow AR</strong> operates along the time axis and predicts the primary semantic codebook.</li>
    1148. 

  1148. <li><strong>Fast AR</strong> generates the remaining 9 residual codebooks at each time step, reconstructing fine-grained acoustic detail.</li>
    1149. 

  1149. </ul>
    1150. 

  1150. <p>This asymmetric design — 4B parameters along the time axis, 400M parameters along the depth axis — keeps inference efficient while preserving audio fidelity.</p>
    1151. 

  1151. <h3 id="reinforcement-learning-alignment">Reinforcement Learning Alignment</h3>
    1152. 

  1152. <p>S2 uses Group Relative Policy Optimization (GRPO) for post-training alignment. The same models used to filter and annotate training data are directly reused as reward models during RL — eliminating distribution mismatch between pre-training data and post-training objectives. The reward signal combines semantic accuracy, instruction adherence, acoustic preference scoring, and timbre similarity.</p>
    1153. 

  1153. <h3 id="production-streaming-via-sglang">Production Streaming via SGLang</h3>
    1154. 

  1154. <p>Because the Dual-AR architecture is structurally isomorphic to standard autoregressive LLMs, S2 directly inherits all LLM-native serving optimizations from SGLang — including continuous batching, paged KV cache, CUDA graph replay, and RadixAttention-based prefix caching.</p>
    1155. 

  1155. <p>On a single NVIDIA H200 GPU:</p>
    1156. 

  1156. <ul>
    1157. 

  1157. <li><strong>Real-Time Factor (RTF):</strong> 0.195</li>
    1158. 

  1158. <li><strong>Time-to-first-audio:</strong> ~100 ms</li>
    1159. 

  1159. <li><strong>Throughput:</strong> 3,000+ acoustic tokens/s while maintaining RTF below 0.5</li>
    1160. 

  1160. </ul>
    1161. 

  1161. <h3 id="multilingual-support">Multilingual Support</h3>
    1162. 

  1162. <p>S2 supports high-quality multilingual text-to-speech without requiring phonemes or language-specific preprocessing. Including:</p>
    1163. 

  1163. <p><strong>English, Chinese, Japanese, Korean, Arabics, German, French...</strong></p>
    1164. 

  1164. <p><strong>AND MORE!</strong></p>
    1165. 

  1165. <p>The list is constantly expanding, check <a href="https://fish.audio/">Fish Audio</a> for the latest releases.</p>
    1166. 

  1166. <h3 id="native-multi-speaker-generation">Native Multi-Speaker Generation</h3>
    1167. 

  1167. <p><img src="../assets/chattemplate.png" width=200%></p>
    1168. 

  1168. <p>Fish Audio S2 allows users to upload reference audio with multi-speaker, the model will deal with every speaker's feature via <code>&lt;|speaker:i|&gt;</code> token. Then you can control the model's performance with the speaker id token, allowing a single generation to include multiple speakers. You no longer need to upload reference audio separately for each speaker.</p>
    1169. 

  1169. <h3 id="multi-turn-generation">Multi-Turn Generation</h3>
    1170. 

  1170. <p>Thanks to the expansion of the model context, our model can now use previous information to improve the expressiveness of subsequent generated content, thereby increasing the naturalness of the content.</p>
    1171. 

  1171. <h3 id="rapid-voice-cloning">Rapid Voice Cloning</h3>
    1172. 

  1172. <p>Fish Audio S2 supports accurate voice cloning using a short reference sample (typically 10–30 seconds). The model captures timbre, speaking style, and emotional tendencies, producing realistic and consistent cloned voices without additional fine-tuning.
    1173. 

  1173. Please refer to <a href="https://github.com/sgl-project/sglang-omni/blob/main/sglang_omni/models/fishaudio_s2_pro/README.md">SGLang-Omni README</a> to use the SGLang server.</p>
    1174. 

  1174. <hr />
    1175. 

  1175. <h2 id="credits">Credits</h2>
    1176. 

  1176. <ul>
    1177. 

  1177. <li><a href="https://github.com/daniilrobnikov/vits2">VITS2 (daniilrobnikov)</a></li>
    1178. 

  1178. <li><a href="https://github.com/fishaudio/Bert-VITS2">Bert-VITS2</a></li>
    1179. 

  1179. <li><a href="https://github.com/innnky/gpt-vits">GPT VITS</a></li>
    1180. 

  1180. <li><a href="https://github.com/b04901014/MQTTS">MQTTS</a></li>
    1181. 

  1181. <li><a href="https://github.com/pytorch-labs/gpt-fast">GPT Fast</a></li>
    1182. 

  1182. <li><a href="https://github.com/RVC-Boss/GPT-SoVITS">GPT-SoVITS</a></li>
    1183. 

  1183. <li><a href="https://github.com/QwenLM/Qwen3">Qwen3</a></li>
    1184. 

  1184. </ul>
    1185. 

  1185. <h2 id="tech-report">Tech Report</h2>
    1186. 

  1186. <div class="language-bibtex highlight"><pre><span></span><code><span id="__span-1-1"><a id="__codelineno-1-1" name="__codelineno-1-1" href="#__codelineno-1-1"></a><span class="nc">@misc</span><span class="p">{</span><span class="nl">fish-speech-v1.4</span><span class="p">,</span>
    1187. 

  1187. </span><span id="__span-1-2"><a id="__codelineno-1-2" name="__codelineno-1-2" href="#__codelineno-1-2"></a><span class="w">      </span><span class="na">title</span><span class="p">=</span><span class="s">{Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis}</span><span class="p">,</span>
    1188. 

  1188. </span><span id="__span-1-3"><a id="__codelineno-1-3" name="__codelineno-1-3" href="#__codelineno-1-3"></a><span class="w">      </span><span class="na">author</span><span class="p">=</span><span class="s">{Shijia Liao and Yuxuan Wang and Tianyu Li and Yifan Cheng and Ruoyi Zhang and Rongzhi Zhou and Yijin Xing}</span><span class="p">,</span>
    1189. 

  1189. </span><span id="__span-1-4"><a id="__codelineno-1-4" name="__codelineno-1-4" href="#__codelineno-1-4"></a><span class="w">      </span><span class="na">year</span><span class="p">=</span><span class="s">{2024}</span><span class="p">,</span>
    1190. 

  1190. </span><span id="__span-1-5"><a id="__codelineno-1-5" name="__codelineno-1-5" href="#__codelineno-1-5"></a><span class="w">      </span><span class="na">eprint</span><span class="p">=</span><span class="s">{2411.01156}</span><span class="p">,</span>
    1191. 

  1191. </span><span id="__span-1-6"><a id="__codelineno-1-6" name="__codelineno-1-6" href="#__codelineno-1-6"></a><span class="w">      </span><span class="na">archivePrefix</span><span class="p">=</span><span class="s">{arXiv}</span><span class="p">,</span>
    1192. 

  1192. </span><span id="__span-1-7"><a id="__codelineno-1-7" name="__codelineno-1-7" href="#__codelineno-1-7"></a><span class="w">      </span><span class="na">primaryClass</span><span class="p">=</span><span class="s">{cs.SD}</span><span class="p">,</span>
    1193. 

  1193. </span><span id="__span-1-8"><a id="__codelineno-1-8" name="__codelineno-1-8" href="#__codelineno-1-8"></a><span class="w">      </span><span class="na">url</span><span class="p">=</span><span class="s">{https://arxiv.org/abs/2411.01156}</span><span class="p">,</span>
    1194. 

  1194. </span><span id="__span-1-9"><a id="__codelineno-1-9" name="__codelineno-1-9" href="#__codelineno-1-9"></a><span class="p">}</span>
    1195. 

  1195. </span><span id="__span-1-10"><a id="__codelineno-1-10" name="__codelineno-1-10" href="#__codelineno-1-10"></a>
    1196. 

  1196. </span><span id="__span-1-11"><a id="__codelineno-1-11" name="__codelineno-1-11" href="#__codelineno-1-11"></a><span class="nc">@misc</span><span class="p">{</span><span class="nl">liao2026fishaudios2technical</span><span class="p">,</span>
    1197. 

  1197. </span><span id="__span-1-12"><a id="__codelineno-1-12" name="__codelineno-1-12" href="#__codelineno-1-12"></a><span class="w">      </span><span class="na">title</span><span class="p">=</span><span class="s">{Fish Audio S2 Technical Report}</span><span class="p">,</span><span class="w"> </span>
    1198. 

  1198. </span><span id="__span-1-13"><a id="__codelineno-1-13" name="__codelineno-1-13" href="#__codelineno-1-13"></a><span class="w">      </span><span class="na">author</span><span class="p">=</span><span class="s">{Shijia Liao and Yuxuan Wang and Songting Liu and Yifan Cheng and Ruoyi Zhang and Tianyu Li and Shidong Li and Yisheng Zheng and Xingwei Liu and Qingzheng Wang and Zhizhuo Zhou and Jiahua Liu and Xin Chen and Dawei Han}</span><span class="p">,</span>
    1199. 

  1199. </span><span id="__span-1-14"><a id="__codelineno-1-14" name="__codelineno-1-14" href="#__codelineno-1-14"></a><span class="w">      </span><span class="na">year</span><span class="p">=</span><span class="s">{2026}</span><span class="p">,</span>
    1200. 

  1200. </span><span id="__span-1-15"><a id="__codelineno-1-15" name="__codelineno-1-15" href="#__codelineno-1-15"></a><span class="w">      </span><span class="na">eprint</span><span class="p">=</span><span class="s">{2603.08823}</span><span class="p">,</span>
    1201. 

  1201. </span><span id="__span-1-16"><a id="__codelineno-1-16" name="__codelineno-1-16" href="#__codelineno-1-16"></a><span class="w">      </span><span class="na">archivePrefix</span><span class="p">=</span><span class="s">{arXiv}</span><span class="p">,</span>
    1202. 

  1202. </span><span id="__span-1-17"><a id="__codelineno-1-17" name="__codelineno-1-17" href="#__codelineno-1-17"></a><span class="w">      </span><span class="na">primaryClass</span><span class="p">=</span><span class="s">{cs.SD}</span><span class="p">,</span>
    1203. 

  1203. </span><span id="__span-1-18"><a id="__codelineno-1-18" name="__codelineno-1-18" href="#__codelineno-1-18"></a><span class="w">      </span><span class="na">url</span><span class="p">=</span><span class="s">{https://arxiv.org/abs/2603.08823}</span><span class="p">,</span><span class="w"> </span>
    1204. 

  1204. </span><span id="__span-1-19"><a id="__codelineno-1-19" name="__codelineno-1-19" href="#__codelineno-1-19"></a><span class="p">}</span>
    1205. 

  1205. </span></code></pre></div>
    1206. 

  1206. 

  1207. 

  1208. 

  1209. 

  1210. 

  1211. 

  1212. 

  1213. 

  1214. 

  1215. 

  1216. 

  1217. 

  1218.                 
    1219. 

  1219.               </article>
    1220. 

  1220.             </div>
    1221. 

  1221.           
    1222. 

  1222.           
    1223. 

  1223. <script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
    1224. 

  1224.         </div>
    1225. 

  1225.         
    1226. 

  1226.       </main>
    1227. 

  1227.       
    1228. 

  1228.         <footer class="md-footer">
    1229. 

  1229.   
    1230. 

  1230.     
    1231. 

  1231.       
    1232. 

  1232.       <nav class="md-footer__inner md-grid" aria-label="Footer" >
    1233. 

  1233.         
    1234. 

  1234.         
    1235. 

  1235.           
    1236. 

  1236.           <a href="install/" class="md-footer__link md-footer__link--next" aria-label="Next: Installation">
    1237. 

  1237.             <div class="md-footer__title">
    1238. 

  1238.               <span class="md-footer__direction">
    1239. 

  1239.                 Next
    1240. 

  1240.               </span>
    1241. 

  1241.               <div class="md-ellipsis">
    1242. 

  1242.                 Installation
    1243. 

  1243.               </div>
    1244. 

  1244.             </div>
    1245. 

  1245.             <div class="md-footer__button md-icon">
    1246. 

  1246.               
    1247. 

  1247.               <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M4 11v2h12l-5.5 5.5 1.42 1.42L19.84 12l-7.92-7.92L10.5 5.5 16 11z"/></svg>
    1248. 

  1248.             </div>
    1249. 

  1249.           </a>
    1250. 

  1250.         
    1251. 

  1251.       </nav>
    1252. 

  1252.     
    1253. 

  1253.   
    1254. 

  1254.   <div class="md-footer-meta md-typeset">
    1255. 

  1255.     <div class="md-footer-meta__inner md-grid">
    1256. 

  1256.       <div class="md-copyright">
    1257. 

  1257.   
    1258. 

  1258.     <div class="md-copyright__highlight">
    1259. 

  1259.       Copyright &copy; 2023-2025 by Fish Audio
    1260. 

  1260.     </div>
    1261. 

  1261.   
    1262. 

  1262.   
    1263. 

  1263.     Made with
    1264. 

  1264.     <a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
    1265. 

  1265.       Material for MkDocs
    1266. 

  1266.     </a>
    1267. 

  1267.   
    1268. 

  1268. </div>
    1269. 

  1269.       
    1270. 

  1270.         
    1271. 

  1271. <div class="md-social">
    1272. 

  1272.   
    1273. 

  1273.     
    1274. 

  1274.     
    1275. 

  1275.     
    1276. 

  1276.     
    1277. 

  1277.       
    1278. 

  1278.       
    1279. 

  1279.     
    1280. 

  1280.     <a href="https://discord.gg/Es5qTB9BcN" target="_blank" rel="noopener" title="discord.gg" class="md-social__link">
    1281. 

  1281.       <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M492.5 69.8c-.2-.3-.4-.6-.8-.7-38.1-17.5-78.4-30-119.7-37.1-.4-.1-.8 0-1.1.1s-.6.4-.8.8c-5.5 9.9-10.5 20.2-14.9 30.6-44.6-6.8-89.9-6.8-134.4 0-4.5-10.5-9.5-20.7-15.1-30.6-.2-.3-.5-.6-.8-.8s-.7-.2-1.1-.2C162.5 39 122.2 51.5 84.1 69c-.3.1-.6.4-.8.7C7.1 183.5-13.8 294.6-3.6 404.2c0 .3.1.5.2.8s.3.4.5.6c44.4 32.9 94 58 146.8 74.2.4.1.8.1 1.1 0s.7-.4.9-.7c11.3-15.4 21.4-31.8 30-48.8.1-.2.2-.5.2-.8s0-.5-.1-.8-.2-.5-.4-.6-.4-.3-.7-.4c-15.8-6.1-31.2-13.4-45.9-21.9-.3-.2-.5-.4-.7-.6s-.3-.6-.3-.9 0-.6.2-.9.3-.5.6-.7c3.1-2.3 6.2-4.7 9.1-7.1.3-.2.6-.4.9-.4s.7 0 1 .1c96.2 43.9 200.4 43.9 295.5 0 .3-.1.7-.2 1-.2s.7.2.9.4c2.9 2.4 6 4.9 9.1 7.2.2.2.4.4.6.7s.2.6.2.9-.1.6-.3.9-.4.5-.6.6c-14.7 8.6-30 15.9-45.9 21.8-.2.1-.5.2-.7.4s-.3.4-.4.7-.1.5-.1.8.1.5.2.8c8.8 17 18.8 33.3 30 48.8.2.3.6.6.9.7s.8.1 1.1 0c52.9-16.2 102.6-41.3 147.1-74.2.2-.2.4-.4.5-.6s.2-.5.2-.8c12.3-126.8-20.5-236.9-86.9-334.5zm-302 267.7c-29 0-52.8-26.6-52.8-59.2s23.4-59.2 52.8-59.2c29.7 0 53.3 26.8 52.8 59.2 0 32.7-23.4 59.2-52.8 59.2m195.4 0c-29 0-52.8-26.6-52.8-59.2s23.4-59.2 52.8-59.2c29.7 0 53.3 26.8 52.8 59.2 0 32.7-23.2 59.2-52.8 59.2"/></svg>
    1282. 

  1282.     </a>
    1283. 

  1283.   
    1284. 

  1284.     
    1285. 

  1285.     
    1286. 

  1286.     
    1287. 

  1287.     
    1288. 

  1288.       
    1289. 

  1289.       
    1290. 

  1290.     
    1291. 

  1291.     <a href="https://hub.docker.com/r/fishaudio/fish-speech" target="_blank" rel="noopener" title="hub.docker.com" class="md-social__link">
    1292. 

  1292.       <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M349.9 236.3h-66.1v-59.4h66.1zm0-204.3h-66.1v60.7h66.1zm78.2 144.8H362v59.4h66.1zm-156.3-72.1h-66.1v60.1h66.1zm78.1 0h-66.1v60.1h66.1zm276.8 100c-14.4-9.7-47.6-13.2-73.1-8.4-3.3-24-16.7-44.9-41.1-63.7l-14-9.3-9.3 14c-18.4 27.8-23.4 73.6-3.7 103.8-8.7 4.7-25.8 11.1-48.4 10.7H2.4c-8.7 50.8 5.8 116.8 44 162.1 37.1 43.9 92.7 66.2 165.4 66.2 157.4 0 273.9-72.5 328.4-204.2 21.4.4 67.6.1 91.3-45.2 1.5-2.5 6.6-13.2 8.5-17.1zm-511.1-27.9h-66v59.4h66.1v-59.4zm78.1 0h-66.1v59.4h66.1zm78.1 0h-66.1v59.4h66.1zm-78.1-72.1h-66.1v60.1h66.1z"/></svg>
    1293. 

  1293.     </a>
    1294. 

  1294.   
    1295. 

  1295.     
    1296. 

  1296.     
    1297. 

  1297.     
    1298. 

  1298.     
    1299. 

  1299.       
    1300. 

  1300.       
    1301. 

  1301.     
    1302. 

  1302.     <a href="http://qm.qq.com/cgi-bin/qm/qr?_wv=1027&k=jCKlUP7QgSm9kh95UlBoYv6s1I-Apl1M&authKey=xI5ttVAp3do68IpEYEalwXSYZFdfxZSkah%2BctF5FIMyN2NqAa003vFtLqJyAVRfF&noverify=0&group_code=593946093" target="_blank" rel="noopener" title="qm.qq.com" class="md-social__link">
    1303. 

  1303.       <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M434.1 420.4c-11.5 1.4-44.9-52.7-44.9-52.7 0 31.3-16.1 72.2-51 101.8 16.8 5.2 54.8 19.2 45.8 34.4-7.3 12.3-125.5 7.9-159.6 4-34.1 3.8-152.3 8.3-159.6-4-9-15.2 28.9-29.2 45.8-34.4-34.9-29.5-51.1-70.4-51.1-101.8 0 0-33.3 54.1-44.9 52.7-5.4-.6-12.4-29.6 9.3-99.7 10.3-33 22-60.5 40.1-105.8C60.9 98 109.2-.1 224.3-.1 338-.1 387.5 96 384.6 214.9c18.1 45.2 29.9 72.9 40.1 105.8 21.8 70.1 14.7 99.1 9.3 99.7z"/></svg>
    1304. 

  1304.     </a>
    1305. 

  1305.   
    1306. 

  1306. </div>
    1307. 

  1307.       
    1308. 

  1308.     </div>
    1309. 

  1309.   </div>
    1310. 

  1310. </footer>
    1311. 

  1311.       
    1312. 

  1312.     </div>
    1313. 

  1313.     <div class="md-dialog" data-md-component="dialog">
    1314. 

  1314.       <div class="md-dialog__inner md-typeset"></div>
    1315. 

  1315.     </div>
    1316. 

  1316.     
    1317. 

  1317.     
    1318. 

  1318.     
    1319. 

  1319.       
    1320. 

  1320.       
    1321. 

  1321.       <script id="__config" type="application/json">{"annotate": null, "base": ".", "features": ["content.action.edit", "content.action.view", "navigation.tracking", "navigation.footer", "search", "search.suggest", "search.highlight", "search.share", "content.code.copy"], "search": "assets/javascripts/workers/search.2c215733.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
    1322. 

  1322.     
    1323. 

  1323.     
    1324. 

  1324.       <script src="assets/javascripts/bundle.79ae519e.min.js"></script>
    1325. 

  1325.       
    1326. 

  1326.     
    1327. 

  1327.   </body>
    1328. 

  1328. </html>
    1329.