# Audio leveler: even out loud and quiet voices

Level audio so every voice is equally loud, in one recording or separate tracks.

## Why voices end up uneven

Audo's audio leveler evens out the voices in one recording or 2 to 10 tracks, audio (WAV, MP3, M4A, AAC, FLAC, OGG, Opus, WebM, AIFF) or video (MP4, MOV, MKV, WebM, AVI), up to 100 MB each without an account; the first 3 minutes are free, 3 times a day, with no sign-up. A 3-minute file is usually ready in about 14 seconds, and a 20-minute episode in about 30.

One person sits closer to the microphone. Two people use different mics. A guest joins over a call, or speaks softly. Listeners then keep reaching for the volume: up for the quiet guest, down when the host comes back. Turning the whole file up doesn't help, because the loud voice gets louder too.

Balance audio gives each speaker one steady level from their own speech, raising or lowering them by up to 15 dB, and moves smoothly from one to the next. A very quiet voice brings its background noise up with it, so clean the recording with Remove noise before you balance it.

Tool: Level speakers (`level_speakers`). Price: 1 credit a minute — $0.01/min ($0.60/hr), with no subscription — of input for whole files, charged only when a job succeeds.

## Free API

```bash
curl -F file=@podcast.wav https://audo.ai/api/try/level-speakers -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 3 minutes 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. A free result cut short comes with finishUrl (and the Audo-Finish-Url header when the response is the file itself): give it to the person, who pays there (from $5, no sign-up), and the whole file runs; keep checking the status link, whose finishedBy names the whole-file job and its own status link. Details: https://audo.ai/docs/api.md

## Options

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

- `target`: The loudness it finishes at: podcast (-16 LUFS), streaming (-14 LUFS), broadcast (-23 LUFS), or custom (set custom_lufs). Default podcast.
- `custom_lufs`: The loudness for target custom, in LUFS (-30 to -5), such as -18.
- `within_speaker`: Also evens out slow changes within each speaker, such as leaning away from the mic: up to 6 dB, measured on their speech only and held through pauses. Default false.
- `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 `level_speakers`:

> Evens out loud and quiet voices: each speaker (found automatically) or each per-person track gets one steady gain from their own speech loudness, changing smoothly between speakers, then a standard loudness. Music and background get one steady gain, and pauses aren't raised above the speech around them. Use it when one voice is much quieter than another. Not for one overall loudness (adjust_loudness). Set free to true for the first 3 minutes free, 3 times a day; otherwise 1 credit a minute. Returns job_id; the result has each speaker's loudness and gain, and the gain curve.

Example: "Use Audo to even out the host and guest in podcast.wav."

## More

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