
Fish Audio
The most expressive, emotionally controllable real-time voice model
About Fish Audio
Fish Audio is what happens when an open source speech model grows a business around it. The company published Fish Speech, a text to speech model that now carries more than 32,000 GitHub stars, then built a hosted platform on the traffic that model already attracted. The result covers text to speech, voice cloning from roughly fifteen seconds of reference audio, speech to text, voice conversion and audio separation, sold both as a consumer web studio and as a low latency streaming API that other AI companies build on top of.
Start in the web studio, where you either pick a voice from the community library or clone one from a reference clip of about fifteen seconds. Write your text and place emotion tags inline where you want the delivery to shift, then generate. Output is metered in credits, and the platform documents that a minute of generation costs roughly 600 to 625 credits, so a tier translates directly into minutes rather than an abstract quota.
- •Inline Emotion Tags - Direct delivery with tags for angry, sad, embarrassed, whispering, soft, breathy and excited rather than accepting flat output
- •Non-verbal Effect Tags - Laughing, sighing, panting and explicit pauses written directly into the script
- •Fifteen Second Voice Cloning - Enhanced voice cloning listed on every tier including the free one
- •Two Million Voice Library - A browsable community library of user uploaded voices across 30 or more languages
- •Low Latency Streaming API - Documented Python and TypeScript SDKs built for conversational agents, used in production by HeyGen, LiveKit, Retell AI and Telnyx
Developers building voice agents are the core audience, particularly anyone who has hit the latency ceiling of a general purpose text to speech API or the price ceiling of the incumbent. At the entry paid tier the per minute cost undercuts the established players by a wide margin, which matters most for products where every user session generates audio.
Pricing
$0 - $999/mo
Plus $7.50 for the first period, then $15/mo; Pro $50 for the first period, then $100/mo
- Free Tier$0/mo
- Plus$15/mo
- Pro$100/mo
- Max$999/mo
- EnterpriseContact sales
Unchanged since August 2026
























































