Fish Audio's top voice model is $0 until November 30, voice cloning and 83 languages included
Fish Audio lets developers call its flagship text-to-speech model, S2.1 Pro, for free through November 30, 2026 by using the model string s2.1-pro-free. It's the same model as the paid s2.1-pro, with 83 languages, voice cloning and bracket-style emotion and delivery tags, on the same API endpoint. There's no hard character cap, only a fair-use policy. The trade-offs: no uptime or latency guarantee, and free requests may be used to improve Fish Audio's models. Claude Code or any other coding agent can wire it into a project with one API call.
Why it matters
Natural-sounding voice is often the priciest part of a voice agent or narrated video. Nearly four weeks of the full model for free is enough to build and test a real prototype.
Who it's for
Developers prototyping voice agents, narration, dubbing or read-aloud features, plus small businesses testing TTS.
How to try it
- Create a Fish Audio account and get an API key from the developer page.
- Ask Claude Code to call Fish Audio's TTS API with model set to s2.1-pro-free. The paid s2.1-pro model still bills, so check the spelling.
- Expect occasional slowdowns, since there's no latency guarantee, and don't send private audio you wouldn't want used for training.
- Set a reminder for November 30 to switch to paid S2.1 Pro or another provider.
Plan & availability: Free for anyone with a Fish Audio API key through November 30, 2026, with no card required, under a fair-use policy. Fish Audio says it's for testing, prototyping, development and smaller businesses, and products making over $1M a year should contact Fish Audio first. Afterwards, paid S2.1 Pro is $15 per million characters. Checked on Fish Audio's blog, developer page and docs changelog on November 5, 2026.
Source: Fish Audio on fish.audio ↗
Written by AgentStackList from the original post. Checked Nov 5, 2026. Features, plans and availability can change, so confirm on the source before you rely on it.
freefish-audiotext-to-speechvoiceapi
More Claude tricks
- Tencent's new open model Hy4 is free in its CodeBuddy and WorkBuddy agents until November 15, and half price on its API · Nov 5
- StepFun's whole StepAudio 3 voice lineup is free on its API until November 8: realtime calls, voice cloning and AI music · Nov 5
- $100 of speech-to-text and text-to-speech, no card: Speechmatics gives new sign-ups a credit that lasts 12 months · Nov 5
- Alibaba open-sourced qz, a browser agent that works inside the Chrome you're already logged into, and Claude Code can hand it tasks · Nov 5
Agent Stack Weekly · free
Get the week's best AI tricks
Limit and pricing changes, new MCP servers, and setup fixes for Claude Code, Codex, Cursor, Copilot and Antigravity.
No spam. Unsubscribe anytime. Read past issues