# Audo: audio tools for people and agents

Audo makes simple audio and video tools, for you and your AI assistant. Remove noise, transcribe, cut, convert, and more, on the web or from ChatGPT, Claude, and coding agents.

Response handling: inspect HTTP status and Content-Type before naming any response.body as media. Handle 202 jobs, 200 JSON manifests and errors with the complete client at https://audo.ai/docs/api#responses.

Remove noise, enhance voices, transcribe, align a script, cut, remove silence, set loudness, convert, and join audio or video files. Use each tool on the website, from ChatGPT, Claude, or a coding agent, or with one curl request. About Audo: https://audo.ai/about.md

## Tools

- [Remove noise](https://audo.ai/noise-removal.md): Turns down background noise, hiss, and hum, keeping the speaker's own voice: it filters the recording and adds nothing. Then sets the whole file to a standard loudness (−16 LUFS). Made for voices: it turns down music and other sounds too. 3 credits a minute. Free for the first minute, 3 times a day.
  `curl -F file=@interview.wav https://audo.ai/api/try/remove-noise -D response.headers -o response.body`
- [Enhance voice](https://audo.ai/remove-echo.md): Rebuilds the voice, for echo, phone calls, and poor recordings: removes echo, noise, and distortion and restores muffled speech, then sets the whole file to a standard loudness (−16 LUFS). Made for voices: music and other sounds are removed too. Its other pages: [Audio enhancer](https://audo.ai/audio-enhancer.md). 3 credits a minute. Free for the first minute, 3 times a day.
  `curl -F file=@lecture.wav https://audo.ai/api/try/enhance-voice -D response.headers -o response.body`
- [Transcribe](https://audo.ai/transcribe.md): Text with a time for every word, in 60 languages. Labels who speaks when: Speaker 1, Speaker 2, and so on. 2 credits a minute. Free for the first 2 minutes, 3 times a day.
  `curl -F file=@interview.mp3 -F format=srt https://audo.ai/api/try/transcribe -D response.headers -o response.body`
- [Align a script](https://audo.ai/text-to-srt.md): Lines up a script you already have with the audio, word by word. 2 credits a minute. Free for the first 2 minutes, 3 times a day.
  `curl -F file=@talk.mp3 -F script=@script.txt -F format=srt https://audo.ai/api/try/align-script -D response.headers -o response.body`
- [Cut](https://audo.ai/audio-cutter.md): Trims, removes, or keeps parts of a file by time. 1 credit a minute. Free for the first 3 minutes, 3 times a day.
  `curl -F file=@episode.mp3 -F mode=remove -F 'ranges=[[0,12.5]]' https://audo.ai/api/try/cut -D response.headers -o response.body`
- [Remove silence](https://audo.ai/silence-remover.md): Shortens long pauses. You choose how much of each pause to keep. 1 credit a minute. Free for the first 3 minutes, 3 times a day.
  `curl -F file=@episode.wav https://audo.ai/api/try/remove-silence -D response.headers -o response.body`
- [Set loudness](https://audo.ai/volume-booster.md): Sets the level for where it's going: podcasts, YouTube, broadcast, or audiobooks. 1 credit a minute. Free for the first 3 minutes, 3 times a day.
  `curl -F file=@episode.wav -F target=podcast https://audo.ai/api/try/loudness -D response.headers -o response.body`
- [Convert](https://audo.ai/audio-converter.md): Any format to MP3, WAV, M4A, FLAC, OGG, or Opus, including the audio from a video. Its other pages: [Convert MP4 to MP3](https://audo.ai/mp4-to-mp3.md). 1 credit a minute. Free for the first 3 minutes, 3 times a day.
  `curl -F file=@episode.wav -F format=mp3 https://audo.ai/api/try/convert -D response.headers -o response.body`
- [Join files](https://audo.ai/audio-joiner.md): Puts an intro, the episode, and an outro together, in order. 1 credit a minute. Free for the first 3 minutes, 3 times a day.
  `curl -F file=@intro.mp3 -F file=@episode.mp3 -F file=@outro.mp3 https://audo.ai/api/try/join -D response.headers -o response.body`
- Swap a video's audio: Puts a new soundtrack on a video. The picture is copied, so it's fast and loses nothing. 1 credit a minute. Free for the first 3 minutes, 3 times a day.
  `curl -F video=@talk.mp4 -F audio=@talk-clean.wav https://audo.ai/api/try/swap-audio -D response.headers -o response.body`
- [Media info](https://audo.ai/media-info.md): Length, format, loudness, peaks, and noise floor, so you can check before and after. Always free, 20 files a day.
  `curl -F file=@interview.wav https://audo.ai/api/try/media-info -D response.headers -o response.body`
- [Remove filler words](https://audo.ai/remove-filler-words.md): Cuts um, uh, and words said twice, in the pauses between words, keeping a natural pause. Works on video. 2 credits a minute. Free for the first 2 minutes, 3 times a day.
  `curl -F file=@interview.mp3 https://audo.ai/api/try/remove-fillers -D response.headers -o response.body`
- [Level speakers](https://audo.ai/audio-leveler.md): Gives each speaker, or each person's track, one steady level so everyone sounds as loud, keeping music and background as they were. 1 credit a minute. Free for the first 3 minutes, 3 times a day.
  `curl -F file=@podcast.wav https://audo.ai/api/try/level-speakers -D response.headers -o response.body`
- [Mix tracks](https://audo.ai/mix-audio.md): Layers up to 20 tracks with their own volume and start, lines up tracks recorded together, and lowers music under speech. 1 credit a minute. Free for the first 3 minutes, 3 times a day.
  `curl -F file=@voice.wav -F file=@music.mp3 -F 'tracks=[{"role":"voice"},{"role":"music","volume_db":-6}]' -F duck=true https://audo.ai/api/try/mix -D response.headers -o response.body`

## Languages

Transcribe (`transcribe_audio`) and Align a script (`align_script`) and Remove filler words (`remove_fillers`) support 60 languages, detected automatically: af, ar, as, az, bg, bn, bs, ca, cs, da, de, el, en, es, et, fa, fi, fil, fr, gl, gu, he, hi, hu, hy, id, is, it, ja, kk, kn, ko, lt, lv, mk, ml, mr, ms, nb, ne, nl, or, pa, pl, pt, ro, ru, sk, sl, sv, sw, ta, te, th, tr, uk, ur, vi, yue, zh. Every other tool works on the sound, so it works in any language.

## From an assistant

Add the MCP server, https://audo.ai/mcp, and sign in. Setup for ChatGPT, Claude, Cowork, Claude Code, Codex, Cursor, Gemini CLI, VS Code, Copilot CLI, Antigravity, Zed, OpenCode, Raycast: https://audo.ai/setup.md

Prompts to try:

- Remove the background noise from interview.wav, then transcribe it.
- Remove the long pauses from episode-12.mp3 and make it podcast-loud.
- Make SRT captions for launch-video.mp4.
- Pull the audio out of this video as an MP3.

## For agents

No key or account needed for the free part of each file. With an 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:

```bash
curl -F file=@interview.wav https://audo.ai/api/try/remove-noise -D response.headers -o response.body
```

- Every tool: https://audo.ai/llms.txt
- OpenAPI: https://audo.ai/api/openapi.json
- Free and REST API docs: https://audo.ai/docs/api.md

## Pricing

Credits a minute of input: noise removal and voice enhancing 3, transcription and alignment 2, everyday tools 1, media info free. Credit packs and the free tier: https://audo.ai/pricing.md

## Questions

**Is it free?** Yes, to try. Every tool is free for the first minutes of a file, a few times a day, with no sign-up. For longer files, see pricing.

**What happens to my files?** They stay private. Uploads are deleted after 24 hours, and free results after 1 hour.

**Which files work?** Audio as WAV, MP3, M4A, AAC, FLAC, OGG, Opus, WebM, AIFF, and video as MP4, MOV, MKV, WebM, AVI. Up to 100 MB without an account, and 10 GB with one.