# Extract audio from video

Pull the sound out of any video, in the format you need.

## Which format to save

MP3 plays everywhere: phones, cars, podcast apps, and upload forms. M4A suits Apple devices. FLAC keeps every detail in a smaller file than a WAV, and OGG and Opus are small, for the web and for speech.

Most MP4 and MOV videos carry AAC sound: pick M4A and it's copied exactly as it is, with nothing lost, in seconds. The sound in a WebM is usually Opus, which the Opus choice copies the same way. WAV and FLAC lose nothing more either, but they make a bigger file: WAV runs to about 10 MB a minute at CD quality.

Tool: Convert (`convert_audio`). The same tool's other pages: https://audo.ai/audio-converter.md, https://audo.ai/mp4-to-mp3.md, https://audo.ai/m4a-to-mp3.md, https://audo.ai/wav-to-mp3.md, https://audo.ai/mp3-to-wav.md, https://audo.ai/mov-to-mp3.md, https://audo.ai/ogg-to-mp3.md, https://audo.ai/flac-to-mp3.md, https://audo.ai/webm-to-mp3.md, https://audo.ai/aac-to-mp3.md, https://audo.ai/mp4-to-wav.md, https://audo.ai/m4a-to-wav.md, https://audo.ai/mp3-to-ogg.md, https://audo.ai/compress-audio.md. Price: 1 credit a minute of input for whole files, charged only when a job succeeds.

## Free API

```bash
curl -F file=@talk.mov -F format=m4a https://audo.ai/api/try/convert -D response.headers -o response.body
```

Read response.headers and response.body before naming media. Handle 202, 200 JSON and errors with the complete response client at https://audo.ai/docs/api#responses.

Free for the first hour of each file, 10 times a day per person, with no key or account. Uploads up to 100 MB, 2 at once from one address. The response is the result itself; a job that runs longer than about 30 seconds returns 202 with a link to check on it. With an API key (`-H "Authorization: Bearer $AUDO_API_KEY"`), omitting free runs the whole file with credits if the balance covers it, otherwise the free portion if quota remains. Set free=true to prohibit spending; for paid whole files use free=false with an approved positive max_credits. Details: https://audo.ai/docs/api.md

## Options

Form fields with the same names as the MCP tool's inputs:

- `format`: The format to convert to: mp3, wav, m4a, flac, ogg, or opus. Default mp3.
- `bitrate_kbps`: The bitrate for mp3, m4a, ogg, or opus, in kbps (16 to 320), such as 128. Default: chosen for the format.
- `sample_rate`: The sample rate in Hz, such as 44100. Default: the input's.
- `channels`: mono or stereo. Default: the input's.

## Languages

Any language: it works on the sound, not the words.

## From an assistant (MCP)

Add https://audo.ai/mcp and sign in (setup for each assistant: https://audo.ai/setup.md). The tool is `convert_audio`:

> Converts a file to another audio format, or pulls the audio out of a video. Use it when the person needs MP3, WAV, M4A, FLAC, OGG, or Opus. Set free to true to do the first hour at no cost, up to 10 times a day; otherwise it costs 1 credit a minute. Returns job_id; then call get_job.

Example: "Use Audo to extract the audio from talk.mov as an M4A."

## More

- Every tool: https://audo.ai/llms.txt
- OpenAPI: https://audo.ai/api/openapi.json
- This page for people: https://audo.ai/extract-audio-from-video