# AI clip finder: find the best moments in long videos

Drop a podcast, stream, or talk. Get ranked moments ready to cut into clips.

## How it works

1. Upload a long video or audio recording up to 10 GB, such as a podcast, livestream, or webinar.
2. Set Number of clips and Longest clip, and enter a topic in Look for if you want specific moments.
3. Play each ranked card on the page, press Cut clip or Make a Short, or click Copy times.

## Long recordings built for an AI clip finder

Skip scrubbing hour-long timelines by hand and surface standalone stories, hooks, and answers ready for Shorts, Reels, and TikTok.

### Podcasts & interviews: Podcast clip maker for Shorts, Reels, and TikTok

Run this podcast clip finder on full interview episodes to pull self-contained stories and guest quotes without re-watching the whole conversation. Already ran [Podcast transcription](https://audo.ai/podcast-transcription.md)? Carry the transcript over to skip transcribing twice.

### Streams & webinars: Video clip finder for livestreams, panels, and Q&As

Drop a multi-hour stream, webinar, or keynote into the video clip finder and steer Look for toward audience questions or product walkthroughs. On video, Make a Short trims the moment and opens 9:16 speaker tracking in [Reframe video](https://audo.ai/horizontal-to-vertical-video.md).

### Courses & lectures: Highlight finder for training sessions and talks

Set Shortest clip and Longest clip between 15 and 600 seconds so this highlight finder isolates complete explanations rather than cut-off soundbites. Burn styled subtitles onto finished clips next with [Auto captions](https://audo.ai/auto-captions.md).

### Premiere, Resolve & Final Cut: Copy clip times or JSON ranges into your desktop editor

Finishing color and graphics on desktop? Click Copy all times for clean start-to-end lines, download the Clips JSON report, or compare rough-cut workflows in our [Gling alternative](https://audo.ai/guides/gling-alternative.md) and [Descript alternative](https://audo.ai/guides/descript-alternative.md) guides.

## Sentence-aligned moments you can preview before cutting

Audo transcribes speech across 60 languages on video (MP4, MOV, MKV, WebM, AVI) and audio (WAV, MP3, M4A, AAC, FLAC, OGG, Opus, WebM, AIFF) files up to 10 GB and 10 hours signed in, then ranks the strongest standalone passages from Best downward. Every card lists its start and end times, duration, title, and plain-English reason.

Suggested clips snap to exact sentence boundaries inside your Shortest clip and Longest clip bounds, and ranked moments never overlap one another. Play any card in place against the full waveform to hear how the passage starts and lands before cutting.

Reviewing moments first lets you export only the clips worth posting: press Cut clip to trim in [Cut audio](https://audo.ai/audio-cutter.md), press Make a Short for vertical 9:16 video, or run Audo's automated clips workflow via the [REST API](https://audo.ai/docs/api.md) and [MCP server](https://audo.ai/docs/mcp.md) when you want all captioned vertical MP4s rendered in one batch.

Ways to turn ranked moments into finished clips in Audo

| Action | What Audo prepares | Where it goes next |
|---|---|---|
| Cut clip | Opens the browser editor on Cut with your recording trimmed to that moment | Export a clip or desktop editor timeline |
| Make a Short (video) | Cuts the moment and opens vertical 9:16 active-speaker framing | Reframe video and Auto captions |
| Copy times / Clips JSON | Copies start-to-end lines or downloads structured timestamps and reasons | Marker import or custom scripts |
| Automated clips workflow | Finds highlights, cuts, reframes 9:16, burns captions, and sets loudness in one batch | [REST API](https://audo.ai/docs/api.md) or [MCP server](https://audo.ai/docs/mcp.md) |

Tool: Find highlights (`find_highlights`). Price: 4 credits a minute — $0.04/min ($2.40/hr), or $0.01/min ($0.60/hr) with transcript_file_id ($0.03 paid-run min), pay-as-you-go with no monthly subscription — of input for whole files, charged only when a job succeeds.

## Free API

```bash
curl -F file=@episode.mp4 -F count=5 https://audo.ai/api/try/find-highlights -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 minute 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 full job with credits if the balance covers it, otherwise the free allowance if quota remains. Set free=true to prohibit spending; for paid runs 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:

- `count`: Maximum number of ranked, non-overlapping moments. Returns fewer when speech cannot fill that many.
- `min_seconds`: Shortest highlight, in seconds. Default 15.
- `max_seconds`: Longest highlight, in seconds. Default 60.
- `instructions`: What to look for, such as funny moments or the product demo. At most 500 characters.

## Languages

60 languages, detected automatically: `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 `find_highlights`:

> Finds ranked moments in a recording for short clips, with a title, reason, and score for each. Use it to choose what to cut next. Moments stay inside the recording, snap to transcript sentence boundaries, without overlaps. Reuses transcript_file_id or transcribes first. It costs 4 credits a minute, or 1 with transcript_file_id, at least 3 a run, charged only if the job succeeds. Returns the moments and a JSON download link, or job_id for get_job if it takes longer.

Example: "Use Audo to find the 5 best moments in episode.mp4 for short clips."

## Questions

**Is there a free AI clip finder online?** Yes — Audo finds ranked clips in the first minute of each recording for free, 3 times a day, with no sign-up. Whole recordings cost $0.04 a minute ($2.40 an hour), or $0.01 a minute ($0.60 an hour) when reusing a transcript made in Audo (at least $0.03 per paid run), paid once from $5 with no subscription — [see pricing](https://audo.ai/pricing.md).

**How does Audo pick and rank the best moments?** Audo transcribes your recording with word-level timing and scores passages where a standalone story, argument, reaction, or answer lands cleanly. Each ranked card (Best, #2, and downward) snaps to full sentences without mid-sentence cuts or overlaps.

**Does it render Shorts right away, or let me preview clips first?** Audo ranks moments first so you can play each candidate on the page before rendering video. Press Cut clip to trim in the editor, press Make a Short on video to open vertical 9:16 speaker tracking in [Reframe video](https://audo.ai/horizontal-to-vertical-video.md), or run the automated clips workflow via the [API](https://audo.ai/docs/api.md) to batch-render captioned MP4s.

**Can I steer what topics or moments it looks for?** Yes. On Audo, enter up to 500 characters in Look for — such as customer stories, pricing questions, funny banter, or key takeaways — and set Number of clips from 1 to 20.

**How do I reuse an existing transcript from Transcribe audio?** When signed in on Audo's [Transcribe audio](https://audo.ai/transcribe.md) or [Podcast transcription](https://audo.ai/podcast-transcription.md), click Find clips under More from this transcript to carry your recording and transcript over without transcribing again, or pass transcript_file_id in the [transcription API](https://audo.ai/docs/transcription-api.md).

**Why did it find fewer clips than I asked for?** Audo returns only passages that stand on their own without overlapping. If a file is brief, sparse on speech, or constrained by narrow Shortest clip and Longest clip settings, widen the clip lengths under More options.

**Which video and audio formats and recording lengths work?** On Audo, video files (MP4, MOV, MKV, WebM, AVI) and audio recordings (WAV, MP3, M4A, AAC, FLAC, OGG, Opus, WebM, AIFF) upload directly up to 10 GB without an account, and up to 10 hours long when signed in — built for full podcasts, livestreams, webinars, and lectures.

**Can ChatGPT, Claude, or an AI agent find clips automatically?** Yes. [Connect Audo over MCP](https://audo.ai/setup.md) and ask ChatGPT, Claude, Cursor, or Claude Code to run find_highlights on your recording — see [audio and video tools for AI agents](https://audo.ai/guides/audio-and-video-tools-for-ai-agents.md).

## More

- Other cuts: [Remove filler words](https://audo.ai/remove-filler-words.md), [Bleep censor](https://audo.ai/bleep-censor.md), [Cut audio](https://audo.ai/audio-cutter.md), [Remove silence](https://audo.ai/silence-remover.md), [Trim video](https://audo.ai/trim-video.md), [Clean song maker](https://audo.ai/clean-song-maker.md), [Audio redaction](https://audo.ai/audio-redaction.md)
- Related guides: [Descript alternative for transcripts and text edits](https://audo.ai/guides/descript-alternative.md), [Gling alternative for cutting bad takes and pauses](https://audo.ai/guides/gling-alternative.md)
- [All tools](https://audo.ai/all-tools.md)
- [Prices and free limits](https://audo.ai/pricing.md)
- [Set up your assistant](https://audo.ai/setup.md)
- Every tool: https://audo.ai/llms.txt
- OpenAPI: https://audo.ai/api/openapi.json
- This page for people: https://audo.ai/ai-clip-finder?utm_source=markdown&utm_medium=agent
