Fish Audio models now available on Vercel AI Gateway for free

's audio models are now available on AI Gateway. To celebrate the launch, every model is free on AI Gateway for the next 30 days, through September 18.Fish AudioFish Audio

Four models from Fish Audio are available, including their latest text-to-speech model:

How to use models during the offer period

Speech and transcription ship in the current 7 release.AI SDK

Generate spoken audio from text with and write the result:generateSpeech

Transcribe recordings into text with . The audio can be a buffer, a base64 string, or a URL:transcribe

Each segment carries the text and its start and end time in seconds, down to individual words.

You can also try the Fish Audio models without writing any code. Open the , click into a model, and send text or audio to hear or read the result in your browser.models list

For a full overview of how to utilize audio models, refer to the . For more detail on Fish Audio, refer to the for the provider.speech quickstartAI SDK docs

Read more

• (text-to-speech): Built for low-latency streaming; clones a voice from a reference recording.fish-audio/s2.1-pro

• (transcription): Returns the text along with the duration of the audio and timestamped segments, down to individual words.fish-audio/transcribe-1

• (text-to-speech): Covers around eighty languages and takes inline tags, plain-language directions written into the text itself, so you can change how a single word or phrase is delivered instead of setting one style for the whole request.fish-audio/s2-pro

• (text-to-speech): Reads text that can carry markers for emotion, tone, and sound effects.fish-audio/s1

• Using the standard model name (i.e., ) is free, but will automatically begin billing when the offer period ends. fish-audio/s2.1-pro

• To ensure you aren't billed after the free period, add the suffix to the standard name, and the model will stop serving when the offer ends (i.e., ). -freefish-audio/s2.1-pro-free

Text-to-speech

Speech-to-text

Playground