[Fish Audio](/ai-gateway/models/labs/fish-audio) # S2 Pro S2 Pro is Fish Audio's open-source text-to-speech model covering 80+ languages, with natural language prosody control and multi-speaker dialogue in a single request. Your use is subject to Fish Audio's [Terms](https://fish.audio/terms/) & [Privacy](https://fish.audio/privacy/) Policies. Free [Use with AI Gateway](https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai%3Futm_source%3Dgateway-model-page%26utm_campaign%3Dai-gateway-models&title=Get+Started+with+Vercel+AI+Gateway) [View docs](https://vercel.com/docs/ai-gateway) ``` 1import { experimental_generateSpeech as generateSpeech } from 'ai'; 2import { gateway } from '@ai-sdk/gateway'; 3import { writeFile } from 'node:fs/promises'; 4 5const result = await generateSpeech({ 6 model: gateway.speechModel('fish-audio/s2-pro'), 7 text: 'Hello from the Vercel AI Gateway!', 8 // Browse voices at https://fish.audio/app/discovery 9 // Open a voice, then use "Copy Model Id" in its "..." menu. 10 voice: '933563129e564b19a115bedd57b7406a', 11}); 12 13await writeFile('speech.mp3', result.audio.uint8Array); ``` [Read docs](https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk) [Overview](/ai-gateway/models/s2-pro) [About](/ai-gateway/models/s2-pro/about) [Providers](/ai-gateway/models/s2-pro/providers) [Similar](/ai-gateway/models/s2-pro/similar) [FAQ](/ai-gateway/models/s2-pro/faq) ## [Copy link to heading](#playground)Playground Try out S2 Pro by Fish Audio. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days. ![fish-audio logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffish-audio.png%3Fv%3D1785975667162&w=48&q=75)S2 Pro Text The text the model will read aloud. Voice SarahPoloSeleneAdrianEthan ![fish-audio logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffish-audio.png%3Fv%3D1785975667162&w=96&q=75) Your generated audio will appear here ## [Copy link to heading](#providers)Providers Route requests across multiple providers. Copy a provider slug to set your preference. Visit the [docs](/docs/ai-gateway/provider-options) for more info. Using a provider means you agree to their terms, listed under Legal. | Provider | | --- | | Input | Capabilities | ZDR | No Training | Release Date | | | --- | --- | --- | --- | --- | --- | | ![fish-audio logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffish-audio.png%3Fv%3D1785975667162&w=48&q=75) [Fish Audio](/ai-gateway/models/providers/fish-audio) Free Legal:[Terms](https://fish.audio/terms/)•[Privacy](https://fish.audio/privacy/) | Free | | | | 03/09/2026 | | | --- | --- | --- | --- | --- | --- | --- | ## [Copy link to heading](#more-models-by-fish-audio)More models by Fish Audio All Speech Transcription | Model | | --- | | Context | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | Providers | ZDR | No Training | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![fish-audio logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffish-audio.png%3Fv%3D1785975667162&w=48&q=75) [fish-audio/s2.1-pro](/ai-gateway/models/s2.1-pro) | | | | Free | Free | | — | | ![fish-audio logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffish-audio.png%3Fv%3D1785975667162&w=48&q=75) | | | 07/28/2026 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![fish-audio logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffish-audio.png%3Fv%3D1785975667162&w=48&q=75) [fish-audio/transcribe-1](/ai-gateway/models/transcribe-1) | | | | Free | Free | | — | | ![fish-audio logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffish-audio.png%3Fv%3D1785975667162&w=48&q=75) | | | 03/01/2026 | | | ![fish-audio logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffish-audio.png%3Fv%3D1785975667162&w=48&q=75) [fish-audio/s1](/ai-gateway/models/s1) | | | | Free | Free | | — | | ![fish-audio logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffish-audio.png%3Fv%3D1785975667162&w=48&q=75) | | | 10/20/2025 | | ## [Copy link to heading](#about-s2-pro)About S2 Pro S2 Pro is Fish Audio's open-source text-to-speech model, covering more than 80 languages. The release includes the model weights, fine-tuning code, and a complete serving stack, which is what separates it from the hosted-only options in the family. The architecture is a dual autoregressive design over a residual vector-quantized audio codec. A larger model predicts the primary semantic codebook and a smaller one fills in the remaining residual codebooks at each step, which is how it keeps quality high without running one large model over every codebook. Prosody control works the same way as in the S2.1 generation. Direction is written inline in square brackets and interpreted as description rather than matched against a fixed vocabulary, so arbitrary phrasing works. Multi-speaker dialogue is supported in a single request. Integration uses the AI SDK's speech generation function. ## [Copy link to heading](#what-to-consider-when-choosing-a-provider)What To Consider When Choosing a Provider - Configuration: The licence is the thing to check first. S2 Pro is published under Fish Audio's research licence: research and non-commercial use is free, and commercial use requires a separate licence agreement. Open weights here do not mean open commercial rights. - Configuration: S2.1 Pro supersedes this model. It covers three more languages, and listening comparisons favour it, so choose S2 Pro when you specifically want published weights or a self-hosted serving stack, and S2.1 Pro when you want the best available quality through an API. - Configuration: Self-hosting means operating the serving stack yourself. Through AI Gateway you skip that, but then the open weights are not the reason you are choosing this model, and S2.1 Pro is likely the better pick. - Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the [documentation](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr) for details. - Authentication: AI Gateway authenticates requests using an [API key](https://vercel.com/docs/ai-gateway/authentication-and-byok#api-key-authentication) or [OIDC token](https://vercel.com/docs/ai-gateway/authentication-and-byok#oidc-token-authentication). You do not need to manage provider credentials directly. ## [Copy link to heading](#when-to-use-s2-pro)When to Use S2 Pro ### Best for - Open-Weight Voice Work: Published weights and fine-tuning code - Self-Hosted Serving: A released inference stack you can operate - Multilingual Coverage: More than 80 languages - Expressive Direction: Plain-language control rather than a fixed tag list - Custom Fine-Tuning: A published base to build on ### Consider alternatives when - Commercial Use: Requires a separate licence agreement from Fish Audio - Best Available Quality: S2.1 Pro wins head-to-head listening comparisons - Maximum Language Coverage: S2.1 Pro supports three more languages - Hosted-Only Deployments: Open weights bring no benefit if you never self-host ## [Copy link to heading](#conclusion)Conclusion S2 Pro is the open-source generation of Fish Audio's voice models, with published weights, a serving stack, and 80+ language coverage. Point `fish-audio/s2-pro` at AI Gateway to try it, and read the research licence before any commercial deployment.