# Audo
> 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.

## Free, no sign-up
Each tool is free for the first part of a file: one request, no sign-up, 3 times a day per tool. For example, noise removal does the first minute free. Uploads up to 100 MB, 2 at once from one address.
- Remove noise (the first minute free, then 3 credits a minute): curl -F file=@in.wav https://audo.ai/api/try/remove-noise -o out.wav
- Enhance voice (the first minute free, then 3 credits a minute): curl -F file=@in.wav https://audo.ai/api/try/enhance-voice -o out.wav
- Transcribe (the first 2 minutes free, then 2 credits a minute): curl -F file=@in.mp3 https://audo.ai/api/try/transcribe
- Align a script (the first 2 minutes free, then 2 credits a minute): curl -F file=@in.mp3 -F script=@script.txt https://audo.ai/api/try/align-script
- Cut (the first 3 minutes free, then 1 credit a minute): curl -F file=@in.mp3 -F 'ranges=[[0,12.5]]' https://audo.ai/api/try/cut -o out.mp3
- Remove silence (the first 3 minutes free, then 1 credit a minute): curl -F file=@in.wav https://audo.ai/api/try/remove-silence -o out.wav
- Set loudness (the first 3 minutes free, then 1 credit a minute): curl -F file=@in.wav https://audo.ai/api/try/loudness -o out.wav
- Convert (the first 3 minutes free, then 1 credit a minute): curl -F file=@in.wav https://audo.ai/api/try/convert -o out.mp3
- Join files (the first 3 minutes free, then 1 credit a minute): curl -F file=@in1.mp3 -F file=@in2.mp3 https://audo.ai/api/try/join -o out.mp3
- Swap a video's audio (the first 3 minutes free, then 1 credit a minute): curl -F video=@in.mp4 -F audio=@in.wav https://audo.ai/api/try/swap-audio -o out.mp4
- Media info (always free): curl -F file=@in.wav https://audo.ai/api/try/media-info
- Remove filler words (the first 2 minutes free, then 2 credits a minute): curl -F file=@in.mp3 https://audo.ai/api/try/remove-fillers -o out.mp3
- Level speakers (the first 3 minutes free, then 1 credit a minute): curl -F file=@in.wav https://audo.ai/api/try/level-speakers -o out.wav
- Mix tracks (the first 3 minutes free, then 1 credit a minute): curl -F file=@in1.wav -F file=@in2.wav https://audo.ai/api/try/mix -o out.wav
- Every tool, with its options: https://audo.ai/api/openapi.json

## 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.

## Speakers
- Transcribe labels who speaks when (Speaker 1, Speaker 2, and so on) in its JSON, TXT, and VTT, unless `speaker_labels` is false. SRT has no names. Details: https://audo.ai/transcribe.md

## Whole files
- With an API key, the same requests process whole files with credits: add -H "Authorization: Bearer $AUDO_API_KEY". Keys: https://audo.ai/keys
- MCP server (sign in; the same free tier, then credits): https://audo.ai/mcp
- Connect an assistant (ChatGPT, Claude, Cowork, Claude Code, Codex, Cursor, Gemini CLI, VS Code, Copilot CLI, Antigravity, Zed, OpenCode, Raycast): https://audo.ai/setup

## More
- About Audo (who it's for and isn't, limits, who makes it): https://audo.ai/about
- Prices and limits: https://audo.ai/pricing
- API docs: https://audo.ai/docs/api
- Markdown version of any page: add .md to its address, such as https://audo.ai/noise-removal.md