# Transcription through toolfare

> Transcribe a recorded audio or video file from its URL, from Claude, ChatGPT, Cursor, Codex or your own code. Set the spoken language, and turn on speaker separation when more than one person talks. No speech-to-text account of your own; each call is quoted before it runs and paid from one toolfare balance.

Page: https://toolfare.ai/transcription

## 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 transcribe the interview recording at this URL with speakers told apart, then pull out every question the host asked

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 transcript from a recording

Tool: `transcription_transcribe`

Transcribe recorded speech to text

Required parameters: url

Optional parameters: diarize, language, max_seconds

Cost: From $0.129

Ask:
- Transcribe this podcast episode and summarise the main points.
- Transcribe this meeting recording and tell me who said what.
- Turn this Mandarin interview into a text transcript.
## Price

From $0.129 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 have a recording — a meeting, interview, podcast or video — and want its text.
- You need to know who said what, with speakers told apart.
- Your agent should search, quote or summarise what was said in a file.

## Look elsewhere when

- You want the clip re-spoken in another language, not a transcript.
- You want to turn text into speech.
- You want a YouTube video’s details or a channel’s uploads rather than what is said in it.

## Limits

- The input is a URL to an audio or video file that can be fetched; there is no upload of a local file.
- Recorded files only, not live streams.
- `max_seconds` is the expected media length and defaults to one hour; set it close to the real length, and higher for longer files.
- Pay as you go from your toolfare balance, in US dollars; there is no subscription. A call runs when your balance covers its quote.