AI123

Fish Audio

Fish Audio is an AI voice company founded in 2025 in Palo Alto, California, by former NVIDIA researcher Liao Shijia. It grew out of Fish Speech, a widely used open-source project on GitHub. The platform supports text-to-speech and voice cloning in more than 80 languages and serves over 8 million users. On AI, the company develops its in-house S2 speech model series, which ranks among the top in the international TTS-Arena speech synthesis challenge.

AI Models

Drama 3

Fish Audio

Drama 3 is a text-to-speech model from Fish Audio built for directed voice performances. You write the direction in plain language in square brackets before a line, such as [nervous, barely holding it together], and can add sounds and pauses inline or change the delivery of specific words with paired tags like <whisper>. It supports multi-speaker scenes in one request, switching language mid-sentence across 80+ languages in the same voice, and phoneme tags for pinning pronunciation of names and terms.

Context
-
Max output
-
Released
2026-10-13
Input
$2 /M

Transcribe 1 Pro

Fish Audio

Transcribe 1 Pro is a speech-to-text model from Fish Audio tuned for interviews, meetings, and podcasts. It labels speakers with inline speaker markers, preserves emotion and vocal-event cues such as [laughter], detects language automatically, and can return timestamped word-level segments.

Context
-
Max output
-
Released
2026-09-24
Input
$100 /M

Transcribe 1

Fish Audio

Transcribe 1 is a speech-to-text model from Fish Audio. It is suited for audio transcription with automatic language detection and can return timestamped word-level segments when alignment details are requested.

Context
-
Max output
-
Released
2026-07-29
Input
$100 /M

S1

Fish Audio

S1 is a multilingual text-to-speech model from Fish Audio. It is suited for voice applications that need broad emotional expression, using parenthetical controls to guide speaking style across its supported languages.

Context
-
Max output
-
Released
2026-07-29
Input
$15 /M

S2 Pro

Fish Audio

S2 Pro is a multilingual text-to-speech model from Fish Audio. It is suited for expressive narration and multi-speaker dialogue, with natural-language controls for speaking style and emotion.

Context
-
Max output
-
Released
2026-07-29
Input
$15 /M

S2.1 Pro

Fish Audio

S2.1 Pro is a production-oriented text-to-speech model from Fish Audio. It is suited for multilingual voice applications, expressive narration, and dialogue synthesis, with open-ended natural-language controls for speaking style and emotion.

Context
-
Max output
-
Released
2026-07-29
Input
$15 /M

All Companies

View all
Browse companies
1X TechnologiesAddverb TechnologiesAeiROBOTAgility RoboticsAI21 LabsAnthropicANYboticsApptronikBlack Forest LabsBooster RoboticsBoston DynamicsCartesiaCognitionCohereCursor (Anysphere)ElevenLabsEngineered ArtsFigure AIGhost RoboticsHexagon RoboticsHugging FaceHumanoidIBMInworldKawada RoboticsKreaLightricksLiquid AILuma LabsMetaMidjourneyMiniMaxMistral AIMurf AINaverNEURA RoboticsOpenAIPAL RoboticsPerplexityPollen RoboticsPoolsideRainbow RoboticsRecraftReka AIRichtech RoboticsRunwaySakana AISharpaSpeechifyStability AISunoTeslaTypeSafe AIUdioUpstageVinMotionWandercraftxAISevnceQihoo 360CASBOTLejuDEEP RoboticsUnisoundWUBA IntelligenceAmazonJD.comYIJIAHEENGINEAIYOBOTICSUBTECHUniX AIViHeroGalileo TechFourierHecbotMICBOTPHYBOTBeijing Humanoid Robot Innovation CenterSpirit AIHuaweiDroidUpSenseTimeEIRTianlian RobotESTUN CODROIDElephant RoboticsAiMOGAByteDanceUnitreeFuwei IntelligenceXiaomiXPENGPaXiniKEPLERMicrosoftKuaishouChengdu Humanoid Robot Innovation CenterTopstarKEENONDigiTStandard RobotsKunlun TechRobotEraAstribotGALAXEAPUDUAgiBotAI2 RoboticsZ.aiGENISOM AIMoonshot AIYQBionicsNEXWISENoetix RoboticsPNDboticsHanson RoboticsFaraday FutureRobintNAVIAIDeepSeekCoreneticPsiBotLINXAIHaribitShengShu TechnologyBaichuan AIBaiduHCFAiFLYTEKAlpha Robotics4ParadigmVbotNetEaseAimagicrobotMeituanLenovo DaystarTencentX Square RobotNVIDIAAppleJingChu RobotHOWXINGWEILANAnt GroupGoogleCNBotDOBOTCloudMindsLimX DynamicsLi-GongKingsoft OfficeGalbotREEMANMirrorMetekStepFunAlibabaIIMT01.AIZerithModelBestLingyi iTechAheadFormMagicLabLumos Robotics