Get a Transcript From a Twitch Clip or VOD
Streams are long and clips are fast, and neither leaves you anything to read — no way to search a moment, pull a quote, or turn a highlight into a caption. Paste a Twitch clip or VOD link and the audio comes back as timestamped text, with optional speaker labels so a co-stream reads as a conversation. Public links only; no Twitch login is ever requested.
- AI transcription
- 98 Languages
- Encrypted; we never train AI on your files
Start with your recording
Drop an audio or video file here, or click to choose.
What you get: a real transcript
Unedited output from a 64-second interview with two speakers (synthetic voices), transcribed with speaker detection on. Only the first lines are shown.
SPEAKER_00 (0:00) Welcome back to Small Shop Stories. SPEAKER_00 (0:02) Today I'm talking to Maya, who runs a tiny bakery on the SPEAKER_00 (0:05) corner of Mill Street. SPEAKER_01 (0:07) Thanks for having me. SPEAKER_01 (0:08) It's really small, just two ovens and a counter. SPEAKER_00 (0:12) So how does a normal day start for you?
1 00:00:00,000 --> 00:00:01,680 [SPEAKER_00] Welcome back to Small Shop Stories. 2 00:00:02,160 --> 00:00:05,320 [SPEAKER_00] Today I'm talking to Maya, who runs a tiny bakery on the 3 00:00:05,320 --> 00:00:06,320 [SPEAKER_00] corner of Mill Street.
Checked against the script, 4 of 189 words differed — a 2.1% word error rate, counting "80" written for "eighty" as an error — and all 14 speaker turns were labelled correctly. This was clean speech; noisy recordings and people talking over each other score lower. See the full transcript and how it was scored
How it works
- 1
Paste or upload
Paste a link from X, Twitch or Loom — or save the video from Instagram, TikTok or YouTube and upload the file.
- 2
Transcribe
We pull the audio and transcribe it with timestamps, usually in minutes.
- 3
Export
Copy the text, or export TXT, SRT, VTT, PDF or DOCX.
Why ScribeToAny
- Paste public Twitch VOD or clip URLs directly to transcribe live gaming commentary, esports broadcasts, and just-chatting streams.
- Long streams follow your plan's limit — the first 30 minutes on the free plan, up to 6 hours on paid plans — with optional speaker labels for co-streams.
- Exports timestamped transcripts and subtitle cues to help editors quickly locate stream highlights and memorable clips.
Frequently asked questions
Do clips and full VODs both work?
Yes, as long as the link is public. Clips are the safest bet because they stay up; VODs work too, but Twitch removes them after a while, so once a VOD has expired there is nothing left for us to fetch. Sub-only and private videos will not work.
Can it separate two people on a co-stream?
Yes. Turn on Detect speakers and the transcript is split by speaker, so a two-caster clip reads as a back-and-forth rather than one running block. It's a best-effort split by voice, not by account. Speakers come back numbered rather than named, and the labels can't be renamed in the app yet — if you need real names, find-and-replace them in the exported DOCX or TXT.
What formats can I export?
TXT, SRT, VTT, TSV, CSV, JSON, PDF and DOCX. SRT and VTT carry the cue timings, so a clip transcript drops straight back onto the video as subtitles for a YouTube re-upload or a highlight reel.
What happens with a VOD longer than 6 hours?
It isn't rejected, but only the part within your plan's limit is transcribed — the first 30 minutes on the free plan, the first 6 hours on paid plans — and the transcript notes it. For a specific moment in a long stream, a clip of that section is quicker.
Does the transcript include the chat?
No. Only what's spoken in the stream's audio is transcribed; chat messages aren't part of the audio, so they don't appear.