# Audio API for developers

Add Studio voice, noise removal, transcription, and every other Audo tool to your app with one API call. Free to try, then pay as you go, with no subscription.

```bash
curl -H "Authorization: Bearer $AUDO_API_KEY" \
  -F file=@zoom-call.m4a \
  https://audo.ai/api/try/enhance-voice \
  -o zoom-call-studio.wav
```

## What you can build

- **Studio voice on every upload** (`enhance_voice`): Podcast, course, and video apps: turn phone and laptop recordings into clear, studio-quality voice.
- **Clean calls and meetings** (`remove_noise`): Remove fans, traffic, and keyboards from recorded calls before anyone listens back.
- **Transcripts with speakers** (`transcribe_audio`): Searchable text, subtitles, and speaker labels in many languages.
- **Editing in the pipeline** (`remove_silence`): Cut silences and filler words, level speakers, and join clips without a timeline.
- **Ready to publish** (`adjust_loudness`): Hit podcast and streaming loudness targets on every file, automatically.
- **Any format in, any format out** (`convert_audio`): Take MP4, MOV, M4A, and more. Return MP3, WAV, or whatever your app needs.

## Three ways in

- **Free API**: One curl request, no key. Free for the first minutes of a file, a few times a day. https://audo.ai/docs/api#free-api
- **REST API**: Whole files with an API key: large uploads, jobs you can follow, and a price before every run. https://audo.ai/docs/api
- **MCP server**: Give your own agent every Audo tool, with sign-in and prices it can read before it spends. https://audo.ai/docs/mcp

## Pricing

Pay as you go, by the minute, by tool: https://audo.ai/pricing. A job is charged only if it succeeds. Auto-refill tops up the balance with a saved card when it drops below an amount the person picks, up to a monthly limit. Get an API key and set up auto-refill at https://audo.ai/keys.