# Fish Audio API — card for AI agents

Generate speech from text with cloned or library voices, transcribe audio, and design voices.

Maker: Fish Audio · category: Voice (speech-to-text, text-to-speech)

## Price (official page)
- Free tier: s2.1-pro-free model at $0.00 / M UTF-8 bytes
- Usage price: TTS $15.00 / M UTF-8 bytes (s2.1-pro, s2-pro); STT $0.36 / audio hour (transcribe-1-pro); voice design $0.01 / successful request
- Per minute: TTS: $15.00 per 1M UTF-8 bytes, at about 1,000 bytes per minute of English speech (AgentGid conversion from the listed price)
- Pricing page: https://docs.fish.audio/developer-guide/models-pricing/pricing-and-rate-limits (checked 2026-10-09)
- Note: API is pay-as-you-go prepaid with no subscription; concurrency grows with total prepaid (5 requests under $100, 15 at $100+, 50 at $1,000+). s1 model retires December 31, 2026.

## Connect
- Official MCP server: https://docs.fish.audio/overview/mcp
- npm: `npm install fish-audio`
- PyPI: `pip install fish-audio-sdk`
- Repository: https://github.com/fishaudio/fish-audio-python

## Other APIs in this category
- OpenAI Realtime API: https://agentgid.com/apis/openai-realtime/agent.md
- ElevenLabs: https://agentgid.com/apis/elevenlabs/agent.md
- LiveKit: https://agentgid.com/apis/livekit/agent.md
- Deepgram: https://agentgid.com/apis/deepgram/agent.md
- Daily: https://agentgid.com/apis/daily/agent.md

## Links
- AgentGid page: https://agentgid.com/apis/fish-audio/

---
AgentGid's catalog is curated: every entry was checked against the maker's official pages (registry, repository, license and pricing pages) on the date shown; a license value shows the quote it stands on wherever AgentGid has one. Usage numbers come from AgentGid's own scan of public repositories set up for AI coding agents. Claims by makers are reported, not tested by AgentGid.