# Voice cleaner: clean up voice recordings

Clear speech from voice memos, phone calls, lectures, and meetings.

## Memos, calls, and lectures

Each kind of speech recording goes wrong its own way. A voice memo has the phone close, but the room's echo and noise around it. Phone lines carry only a narrow slice of the voice, roughly 300 to 3,400 Hz, so calls sound thin. A lecture recorded from the back of the room is distant and echoey, and meetings bring laptop mics, fans, and keyboards.

The cleaner gives each voice a fuller, closer sound and removes what's around it. You get your file back in the format you put in, ready for Transcribe to turn into text, or for Remove silence to shorten the long pauses. Files can run up to 10 hours, long enough for a full lecture or meeting.

Tool: Enhance voice (`enhance_voice`). The same tool's other pages: https://audo.ai/audio-enhancer.md, https://audo.ai/remove-echo.md, https://audo.ai/audio-cleaner.md. Price: 3 credits a minute of input for whole files, charged only when a job succeeds.

## Free API

```bash
curl -F file=@voice-memo.m4a https://audo.ai/api/try/enhance-voice -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 minute of each file, 3 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:

- `noise_reduction`: How much of the regenerated voice to use, as a percentage. 100 uses all of it; lower values mix back some of the original sound. Default 100.
- `auto_volume`: Sets the whole file to -16 LUFS with one gain, and limits peaks to -1 dBTP. It doesn't balance loud and quiet speakers. Default true.
- `output_format`: The result's format: same (as the input; a video stays a video), wav, mp3, m4a, or flac. Default same.

## 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 `enhance_voice`:

> Regenerates speech: removes echo, noise, and distortion, and restores muffled, phone, or low-quality voices. Then sets the file to -16 LUFS. Made for voices: music and other sounds are removed too. Works on video. Use it for echoey, phone, low-quality, or damaged recordings. Not for plain background noise when the voice is fine (remove_noise keeps the real voice). Set free to true to do the first minute at no cost, up to 3 times a day; otherwise it costs 3 credits a minute, charged only if the job succeeds. Returns job_id; then call get_job.

Example: "Use Audo to clean up the voice in lecture-memo.m4a, then transcribe it."

## More

- Every tool: https://audo.ai/llms.txt
- OpenAPI: https://audo.ai/api/openapi.json
- This page for people: https://audo.ai/voice-cleaner