Fish Audio models now available on Vercel AI Gateway for free
By Steven Van ·
Fish Audio's audio models are now available on AI Gateway.
Vercel's AI Gateway now offers four Fish Audio models, and every one is free through September 18 to mark the launch.
- fish-audio/s2.1-pro: text-to-speech built for low-latency streaming, clones a voice from a reference recording.
- fish-audio/transcribe-1: transcription that returns text plus timestamped segments down to individual words.
- fish-audio/s2-pro: text-to-speech covering around eighty languages, with inline tags to change how a single word or phrase is delivered.
- fish-audio/s1: text-to-speech that reads text carrying markers for emotion, tone, and sound effects.
Text-to-speech normally costs $15.00 per million characters and speech-to-text $0.36 per hour of audio; both are free until the offer ends. Using a model's standard name, such as fish-audio/s2.1-pro, will start billing automatically once the period closes; adding a -free suffix instead makes the model stop serving at that point rather than bill. Speech and transcription work with the current AI SDK 7 release, through generateSpeech and transcribe, and the models can also be tried without code in the Playground.
Vercel
The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.
View Vercel →