# Fish Audio's voices. No Fish Audio account.

Source: https://corespeed.io/integrations/fish-audio

Fish Audio on CoreSpeed gives Claude Code, Codex, Cursor or any MCP agent Fish Audio's speech models and its public voice library, with no Fish Audio account. Your agent picks a library voice or designs a new one, then speaks a script in more than 80 languages, including dialogue with one voice per speaker. Each clip lands in your Drive.

## Set up an agent

Give your agent this line: `set up https://corespeed.io/SKILL.md (read it raw, e.g. with curl)`

It fetches the skill at https://corespeed.io/SKILL.md, adds the CoreSpeed MCP server, signs you in (or up), and keeps the skill for next time. Nothing to connect: Fish Audio is built in. Each call is priced in credits, from your one balance. Create an account: https://app.corespeed.io/sign-up

## Pick the voice. Hear the script

Your agent searches Fish Audio's library for a voice that fits, then reads your script with it. The clip comes back as a link and as a file in your Drive.

You ask your agent: "Find a licensed, warm English narrator in the Fish Audio library. Read this 40-word intro for our demo video with it, and save the MP3 to launch/intro.mp3."

It calls CoreSpeed:

- `media__list_voices`: ok, 356 ms
- `media__generate`: ok, 3820 ms
- `drive__put`: ok, 240 ms

It reads from: Fish Audio.

### Voice-over: Your intro, read by a licensed narrator.

The voice is licensed for commercial work. The MP3 is saved where you asked.

**Done**

- The 40-word intro, read in a warm English voice.

**Next**

- Ask for a slower take, or try a second voice from the list.

_Illustrative example · Fictional script and voice_

Speech and voices: https://corespeed.io/docs/media#speech-and-voices

## Find a voice. Then let it speak

Requests you can make right after setup. The data is fictional.

### Find a licensed voice

Warm narrators, English · Voice library

- Searched: Narrator, English, licensed only
- Each row: A sample to listen to first
- Searching is free

### Design a new voice

A voice from a description · Voice design

- Asked for: A friendly late-night radio host
- Back: Short samples in your Drive
- Billed once per design

### Act out a scene

Two speakers, one call · Dialogue

- Speaker 1: Reid, a whispering engineer
- Speaker 2: Mira, relieved and warm
- One voice per speaker, in order

## Keep your agent. Nothing to connect

One CoreSpeed account, across compatible agents.

1. **Set up CoreSpeed**: Give your agent the setup line. It adds CoreSpeed and signs you in.
2. **Check the price**: Every tool has a rate in credits. Your agent reads it before each call.
3. **Start with one task**: Ask your agent to find a voice and read one short line with it.

Setup guides: Claude Code https://corespeed.io/docs/mcp#claude-code · Codex https://corespeed.io/docs/mcp#codex · Cursor https://corespeed.io/docs/mcp#cursor

## Questions

### Can I use my own voice?

Yes. Put 10 to 30 seconds of one speaker's clean speech in your Drive, with the words it says. Use only voices you have permission to use.

### How is this different from audio generation?

Audio generation lists every music, sound and speech model. This page is about Fish Audio's speech models, its voice library and voice design. Audio generation: https://corespeed.io/integrations/audio-generation

### Which voices should I use for commercial work?

Licensed voices only. The rest of the library is community uploads, and a licensed voice bills at a higher rate than the model alone.

### Do I need an account or API key for Fish Audio?

No. Fish Audio is built into CoreSpeed. Your agent sees its tools after setup, with nothing to connect.

### What does Fish Audio cost?

Each call has a rate in credits, shown before it runs, from your one balance. A failed call costs nothing. Every Fish Audio tool and its price: https://corespeed.io/catalog/fish-audio

### Do I have to switch agents?

No. CoreSpeed adds tools to the agent you already use: Claude Code, Codex, Cursor, or another MCP client. Each one signs in once.

Every tool and price: https://corespeed.io/catalog/fish-audio

## Related pages

- [Audio generation for AI agents](https://corespeed.io/integrations/audio-generation): Give your agent music, sound effect and text to speech models with no API keys. It reads each rate first, and a failed generation costs nothing.
- [Tools](https://corespeed.io/tools): Models, the live web and nine social platforms, on one balance. No account for any of them.
- [Transcription for AI agents](https://corespeed.io/integrations/transcription): Turn a call, an interview or a video into text from your agent, with speaker labels and word timings. No account or API key to set up.

## Sources

- Media docs: speech and voices: https://corespeed.io/docs/media
- Fish Audio catalog: https://corespeed.io/catalog/fish-audio
- The media tool now speaks: https://corespeed.io/blog/the-media-tool-now-speaks
- Fish Audio: https://fish.audio

Reviewed 2026-11-14.

## Links

- Product overview: https://corespeed.io/ (Markdown: https://corespeed.io/index.md)
- All integrations: https://corespeed.io/integrations (Markdown: https://corespeed.io/integrations.md)
- Documentation: https://corespeed.io/docs
- Pricing: https://corespeed.io/pricing (Markdown: https://corespeed.io/pricing.md)
