{"slug": "fish-audio-models-now-available-on-vercel-ai-gateway-for-free", "title": "Fish Audio models now available on Vercel AI Gateway for free", "summary": "Vercel's AI Gateway now offers Fish Audio's four audio models for free through September 18, including text-to-speech and speech-to-text, with standard pricing resuming after the period unless models are used with the '-free' suffix. The free offer covers the s2.1-pro, transcribe-1, s2-pro, and s1 models, and is available via the AI SDK 7 release.", "body_md": "[Fish Audio](https://vercel.com/ai-gateway/models/providers/fish-audio)'s audio models are now available on AI Gateway. To celebrate the launch, every [Fish Audio](https://ai-sdk.dev/providers/ai-sdk-providers/fish-audio#fish-audio-provider) model is free on AI Gateway for the next 30 days, through September 18.\n\nCapability | Regular | Through September 18 |\n|---|---|---|\nText-to-speech | $15.00 per million characters | Free |\nSpeech-to-text | $0.36 per hour of audio | Free |\n\nFour models from Fish Audio are available, including their latest text-to-speech model:\n\n`fish-audio/s2.1-pro`\n\n(text-to-speech): Built for low-latency streaming; clones a voice from a reference recording.\n\n`fish-audio/transcribe-1`\n\n(transcription): Returns the text along with the duration of the audio and timestamped segments, down to individual words.\n\n`fish-audio/s2-pro`\n\n(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.\n\n`fish-audio/s1`\n\n(text-to-speech): Reads text that can carry markers for emotion, tone, and sound effects.\n\n**How to use models during the offer period**\n\nUsing the standard model name (i.e., `fish-audio/s2.1-pro`\n\n) is free, but will automatically begin billing when the offer period ends.\n\nTo ensure you aren't billed after the free period, add the `-free`\n\nsuffix to the standard name, and the model will stop serving when the offer ends (i.e., `fish-audio/s2.1-pro-free`\n\n).\n\nSpeech and transcription ship in the current [AI SDK](https://ai-sdk.dev/providers/ai-sdk-providers/fish-audio#fish-audio-provider) 7 release.\n\nGenerate spoken audio from text with `generateSpeech`\n\nand write the result:\n\nTranscribe recordings into text with `transcribe`\n\n. The audio can be a buffer, a base64 string, or a URL:\n\nEach segment carries the text and its start and end time in seconds, down to individual words.\n\nYou can also try the Fish Audio models without writing any code. Open the [models list](https://vercel.com/ai-gateway/models/providers/fish-audio), click into a model, and send text or audio to hear or read the result in your browser.\n\nFor a full overview of how to utilize audio models, refer to the [speech quickstart](https://vercel.com/docs/ai-gateway/getting-started/speech). For more detail on Fish Audio, refer to the [AI SDK docs](https://ai-sdk.dev/providers/ai-sdk-providers/fish-audio#fish-audio-provider) for the provider.", "url": "https://wpnews.pro/news/fish-audio-models-now-available-on-vercel-ai-gateway-for-free", "canonical_source": "https://vercel.com/changelog/fish-audio-models-now-available-on-ai-gateway-for-free", "published_at": "2026-08-19 00:00:00+00:00", "updated_at": "2026-08-19 22:12:45.922162+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "generative-ai", "natural-language-processing"], "entities": ["Vercel", "Fish Audio", "AI Gateway", "AI SDK"], "alternates": {"html": "https://wpnews.pro/news/fish-audio-models-now-available-on-vercel-ai-gateway-for-free", "markdown": "https://wpnews.pro/news/fish-audio-models-now-available-on-vercel-ai-gateway-for-free.md", "text": "https://wpnews.pro/news/fish-audio-models-now-available-on-vercel-ai-gateway-for-free.txt", "jsonld": "https://wpnews.pro/news/fish-audio-models-now-available-on-vercel-ai-gateway-for-free.jsonld"}}