# Text-based video and audio editor

Drop a recording, get the words, and cut the parts you don't need.

## How it works

1. Add an audio or video file. Pick the spoken language, or leave it on automatic detection, then start transcription at the price or free allowance shown.
2. The editor opens in Transcript mode. Click a word to play from there, or select a passage and choose Cut to remove it from the recording.
3. Listen to the join, restore any words you want back, and export the edited audio or video. You can switch to Timeline for a closer look at a cut.

## Edit the recording through its words

Audo's text-based editor turns speech into a timed transcript you can use to cut a recording. Each word points to a moment in the original file. Select a sentence you don't need and choose Cut: that passage leaves the sound, and the picture leaves with it when you're editing a video. The rest of your recording stays in order.

Text-based video editing suits interviews, spoken presentations, podcast episodes and talking-head recordings. Read through an answer to find a tangent, then listen from the word where it starts before deciding what to remove. The words being spoken light up during playback, and speaker turns help you follow a conversation. Nothing is cut automatically when you open this page's editor.

A transcript editor can mean correcting a written record, or using that record to change the media. Audo does both, with separate actions. Correct fixes the transcript and captions without changing the speaker's voice. Cut removes the selected passage from the recording. You can restore a cut or use Undo, so you can compare the shorter version with what was said before exporting.

Tool: Transcribe (`transcribe_audio`). The same tool's other pages: https://audo.ai/transcribe.md, https://audo.ai/podcast-transcription.md, https://audo.ai/interview-transcription.md, https://audo.ai/srt-file-generator.md. Price: 3 credits a minute — $0.03/min ($1.80/hr), with no subscription — of input for whole files, charged only when a job succeeds.

## Free API

```bash
curl -F file=@interview.mp3 -F verbatim=true -F speaker_labels=true https://audo.ai/api/try/transcribe -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?utm_source=markdown&utm_medium=agent#responses.

Free for the first 2 minutes of each file, 3 times a day per person, with no key or account. Uploads up to 10 GB, 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:

- `language`: The spoken language, as a code such as en or ja. Default: detected.
- `verbatim`: Keeps filler words such as um and uh, so they can be cut later. Default true.
- `speaker_labels`: Labels who speaks when: Speaker 1, Speaker 2, and so on, in the order they first speak, up to 8 people. No names. Default true.
- `format`: what the free API returns: json (default), srt, vtt, or txt.

## Speakers

Transcription labels who speaks when, unless `speaker_labels` is false: Speaker 1, Speaker 2, and so on, numbered in the order people first speak, without real names. It finds at most 8 speakers.

- JSON: every word and sentence has `speaker` (a number from 1), and the transcript has `speaker_count`. A sentence never spans two speakers.
- TXT: with two or more speakers, one paragraph per turn, starting "Speaker 1: ".
- VTT: with two or more speakers, each cue names its speaker in a voice span, such as `<v Speaker 1>`.
- SRT: no names, so it stays clean for YouTube.
- No caption spans two speakers.
- The job's result has `speaker_labels` (`on`, `off`, or `failed`) and `speaker_count`.
- Reading the transcript: MCP `get_transcript` gives `speaker_count` and each sentence's `speaker`; the REST transcript endpoint gives `speakerCount` and `speaker`.

If labeling fails, the job still succeeds with every word, just without speakers: `speaker_labels` is `failed`, and the result has a `warning`.

## Languages

60 languages, detected automatically. To name one, set `language` to its code: `af` Afrikaans, `ar` Arabic, `hy` Armenian, `as` Assamese, `az` Azerbaijani, `bn` Bengali, `bs` Bosnian, `bg` Bulgarian, `yue` Cantonese, `ca` Catalan, `zh` Chinese (Simplified), `cs` Czech, `da` Danish, `nl` Dutch, `en` English, `et` Estonian, `fil` Filipino, `fi` Finnish, `fr` French, `gl` Galician, `de` German, `el` Greek, `gu` Gujarati, `he` Hebrew, `hi` Hindi, `hu` Hungarian, `is` Icelandic, `id` Indonesian, `it` Italian, `ja` Japanese, `kn` Kannada, `kk` Kazakh, `ko` Korean, `lv` Latvian, `lt` Lithuanian, `mk` Macedonian, `ms` Malay, `ml` Malayalam, `mr` Marathi, `ne` Nepali, `nb` Norwegian Bokmål, `or` Odia, `fa` Persian, `pl` Polish, `pt` Portuguese, `pa` Punjabi, `ro` Romanian, `ru` Russian, `sk` Slovak, `sl` Slovenian, `es` Spanish, `sw` Swahili, `sv` Swedish, `ta` Tamil, `te` Telugu, `th` Thai, `tr` Turkish, `uk` Ukrainian, `ur` Urdu, `vi` Vietnamese.

## From an assistant (MCP)

Add https://audo.ai/mcp and sign in (setup for each assistant: https://audo.ai/setup.md). The tool is `transcribe_audio`:

> Transcribes speech in an audio or video file, with a start and end time for every word and who speaks when (Speaker 1, Speaker 2, and so on, in the order they first speak). Use it when the person wants text or captions, or wants to cut by words. Not for lining up a script they already have (align_script). It costs 3 credits a minute, charged only if the job succeeds. Returns TXT, SRT, VTT, and JSON files, which get_transcript reads, or job_id for get_job if it takes longer.

Example: "Use Audo to transcribe interview.mp3 with word timings and keep filler words so I can edit by text."

## Questions

**What is text-based editing?** Text-based editing uses a recording's transcript to choose which moments to keep. In Audo, selecting words and choosing Cut removes the matching audio and video. You edit the content of a spoken recording by reading it, rather than searching for every sentence on a waveform.

**Can I edit audio without a video?** Yes. Audo opens audio-only recordings in the same Transcript mode. Upload WAV, MP3, M4A, AAC, FLAC, OGG, Opus, WebM, AIFF, transcribe the speech, then cut an unwanted sentence from an interview, voice memo or podcast intro. Use Export for the finished sound file.

**Does deleting transcript text cut the video too?** Yes, when you select words and choose Cut. Audo removes that span from both the picture and sound, keeping them together. Check the transition by playing across it; a cut can sound natural while making a visible jump between two frames of a speaker.

**Does correcting a word change the speaker's voice?** No. Correct changes the written transcript and any captions that use it. It does not make the speaker say a new word or synthesize replacement speech. Use Cut when you want to remove the spoken passage, and review the sound before exporting.

**Can I use Audo as a Descript alternative?** For transcribing a recording and cutting it by its words, yes: Audo offers that specific text-based audio and video editing workflow in your browser. That overlap is not a promise that every Descript feature is available. This page gets you straight to the transcript, with cleanup and automatic cuts off until you choose them.

**Is the text-based editor free?** You can try Audo transcription for the first 2 minutes of each file, 3 times a day, without signing up. Transcribing a whole recording costs $0.03 a minute ($1.80 an hour), with no subscription. The editor shows the covered part and offers to transcribe the rest. Editing the words after transcription is free; Export shows the allowance or price for processing your recording. See pricing for each tool.

## More

- Every tool: https://audo.ai/llms.txt
- OpenAPI: https://audo.ai/api/openapi.json
- This page for people: https://audo.ai/text-based-editor?utm_source=markdown&utm_medium=agent