# Audio trimmer: trim and cut audio

Trim MP3s, songs, and other audio: cut the start, the end, or any part.

## Trim, remove, or keep

Audo's audio trimmer and MP3 cutter works on audio (WAV, MP3, M4A, AAC, FLAC, OGG, Opus, WebM, AIFF) and video (MP4, MOV, MKV, WebM, AVI) up to 100 MB without an account, free for the first hour of each file, 10 times a day, with no sign-up. A 4-minute file is usually ready in about 8 seconds, and even an hour-long one in about 14.

Trim: mark the silence or chatter at the start and the end, and cut them out. Remove: mark a cough, a mistake, or an ad break in the middle. Keep: mark only what you want, such as a quote or a chorus, and choose Keep only them. Press Mark a part here while it plays, then drag the part's edges on the waveform or type its times.

For long pauses, Remove silence finds them for you, and Remove filler words cuts the ums. Merge audio joins files one after another, and Transcribe gives the time of every word, to cut by what was said. Audo takes files, not links: to trim your own YouTube video, download it from YouTube Studio first.

Tool: Cut (`cut_audio`). 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=@episode.mp3 -F mode=remove -F 'ranges=[[0,12.5]]' https://audo.ai/api/try/cut -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. 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:

- `ranges`: Time ranges as [start, end] pairs in seconds, such as [[0, 12.5], [300, 312]]. 1 to 100 ranges.
- `mode`: remove deletes the ranges; keep keeps only the ranges. Default remove.
- `output`: joined makes one file; separate makes one file per range. Default joined.
- `crossfade_ms`: A crossfade at each cut, in milliseconds (0 to 200), such as 20. Default 20.

## 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 `cut_audio`:

> Removes or keeps time ranges in an audio or video file, as one file or one file per range. Use it to trim, remove sections, or split. To cut by words, get their times from get_transcript first. 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 of input. Returns job_id; the result maps old times to new ones.

Example: "Use Audo to cut the first 12 seconds and the part from 5:00 to 5:12 out of episode.mp3."

## More

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