Fish Audio S2.1 Pro TTS

Generate MP3 speech with the $0 fair-use s2.1-pro-free API model, 83 languages, a default voice, or an optional Fish Audio Voice ID.

Updated 7/15/20262 code examples

About the Model

Why choose Fish Audio S2.1 Pro?

Choose S2.1 Pro when you need natural speech across many languages without maintaining separate language models. It automatically detects the input language and supports 83 languages.

Core strengths

  • Natural direction: place descriptive cues such as [whispers sweetly], [laugh], or [sigh] inside the text.
  • Reusable voices: create a voice clone once, then pass its Voice ID as reference_id to later TTS requests.
  • Same free-model quality: s2.1-pro-free uses the same model quality and language coverage as s2.1-pro.

What free means

The API model s2.1-pro-free costs $0 for development and testing under unpublished fair-use limits. It has no TTFA or DPA guarantees. This is separate from the website Free Tier, which currently lists 8,000 monthly credits, about 7 minutes, 500 characters per generation, and 3 public voice slots.

Create a Fish Audio account and API key: https://fish.audio/?aff=QNLX47TF37QU6

How to Access for Free (via Fish Audio)

Why use this free TTS endpoint?

It gives you S2.1 Pro quality and 83-language coverage through the $0 s2.1-pro-free model. Language detection is automatic, and cues such as [whisper], [laugh], and [excited] can shape delivery.

How to call it

  • Send JSON to POST https://api.fish.audio/v1/tts.
  • Use Bearer authentication and set the model header to s2.1-pro-free.
  • Omit reference_id for the default voice, or provide a Voice ID for a saved voice.
  • Our Playground fixes output to MP3, limits text to 500 characters, never auto-plays, and retains no audio.

What free means

s2.1-pro-free is an API development model priced at $0 under fair-use limits. Fish Audio publishes no fixed request allowance and provides no TTFA or DPA guarantee. The separate website Free Tier currently lists 8,000 credits per month, about 7 minutes, 500 characters per generation, and 3 public voice slots.

Create a Fish Audio account and API key: https://fish.audio/?aff=QNLX47TF37QU6

📖 View Full Guide

Try it in your browser

Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.

Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.

Code Examples

curl --request POST https://api.fish.audio/v1/tts \
  --header "Authorization: Bearer $FISH_API_KEY" \
  --header "Content-Type: application/json" \
  --header "model: s2.1-pro-free" \
  --data '{"text":"Hello! Welcome to Fish Audio.","format":"mp3"}' \
  --output fish-audio.mp3

Limitations & Caveats

Before sending requests

  • s2.1-pro-free is subject to unpublished fair-use limits and has no TTFA or DPA guarantee.
  • Keep the API key server-side and rotate it immediately if exposed.
  • reference_id is optional; our Playground outputs MP3 and applies its own 500-character limit.
  • Use only voices you own or have permission to use. Read the official TTS API documentation.
← View all free providers for Fish Audio S2.1 Pro

Community Feedback

Comments are tied to your GitHub account — sign in to join the discussion.