# Audio Generation through toolfare

> Two audio tools: one makes a full song with vocals from a text prompt, the other re-voices a speech recording into another voice. Ask from Claude, ChatGPT, Cursor, Codex or your own code; both return a task the agent collects with `get_result`. No music or voice platform account of your own, and each call is quoted before it runs.

Page: https://toolfare.ai/audio-generation

## Use it from your agent

Paste this into Claude Code, Codex, Cursor or any agent with a shell:

> Set up https://toolfare.ai/skill.md, then use toolfare to make a 30-second upbeat acoustic jingle about morning coffee with stable-audio, and tell me the price before you start

Apps without a terminal connect toolfare as an MCP server: https://toolfare.ai/docs#connect

## Use it from a script

```sh
mkdir -p ~/.local/bin
curl -fsSL 'https://toolfare.ai/toolfare/toolfare.mjs' -o ~/.local/bin/toolfare
chmod +x ~/.local/bin/toolfare
export PATH="$HOME/.local/bin:$PATH"
export TOOLFARE_MCP_URL='https://api.toolfare.ai/mcp'
toolfare login
```

Sign in once per machine; the CLI renews the sign-in itself. On a CI runner or another server,
create an API key in the toolfare console and set it as `TOOLFARE_API_KEY` instead of signing in.
Paid calls on one sign-in or key run one at a time. `--max-cost` refuses a call quoted above
that many credits (1,000 credits = $3).

## Tools

### A song from a prompt

Tool: `audio_generation_music`

A full song with vocals from a prompt

Required parameters: model, prompt

Optional parameters: seconds

Cost: From $0.15

Ask:
- Write a short upbeat pop song about launching our app.
- Make a 20-second lo-fi track for the background of our demo video.
- Generate a cheerful jingle with vocals for a coffee brand.

### A recording, in another voice

Tool: `audio_generation_voice_changes`

Speech recording re-voiced into another voice

Required parameters: audio_url, seconds

Optional parameters: model, voice

Cost: From $0.9

Ask:
- Re-voice this voice memo with the Adam voice.
- Change the speaker in this 30-second recording to Rachel.
## Price

From $0.15 Quoted before each call; the final charge follows the returned usage. Pay per call from one balance.

Balances and top-ups are in US dollars. Quotes and `--max-cost` count credits: 1,000 credits = $3 ($0.003 each).

## Use it when

- You need a short song or jingle with vocals for a video, ad or demo.
- You want background music described in words rather than picked from a library.
- You have a speech recording and want the same words in a different voice.

## Look elsewhere when

- You want speech generated from text.
- You want a recording re-spoken in another language.
- You need sound effects. There is no sound-effects tool; the music tool is built for songs.

## Limits

- Asynchronous: both tools return a task, and the audio is collected with `get_result` once it is ready.
- Song length is set only on stable-audio (`seconds`, 20 by default); lyria-3-pro takes no length.
- The voice changer offers two target voices, Rachel and Adam, and needs the source recording’s URL and length in seconds.
- Pay as you go from your toolfare balance, in US dollars; there is no subscription. A call runs when your balance covers its quote.