Drop the video file here — no need to extract the audio first — and get a speaker-labeled transcript with timestamps in about a minute, plus SRT and VTT captions. Private Whisper, no third-party AI, never trained on your uploads. Packs from $4, credits never expire · instant preview with no signup · free account adds 60 minutes.
How it works
No conversion, no audio extraction, no bot. Upload the video and read the transcript.
Any common format works — MP4, MOV, MKV, AVI, WebM, FLV. Screen recording, a clip, a full talk; if it has speech, it transcribes.
Upload it as-is. Transferred over TLS 1.3, encrypted at rest with AES-256. We run open-source Whisper on private infrastructure — nothing leaves to OpenAI, Google, or any third party.
Speaker-labeled transcript with timestamps. Export SRT/VTT for captions, DOCX/TXT for a doc, JSON for automation. Delete the file when you're done.
What you get
Every video transcript comes with the tools to actually use it.
MP4, MOV, MKV, AVI, WebM, FLV, and more — plus audio files. No converting to MP3 or extracting the audio track first.
Download standards-compliant caption files to upload to YouTube or attach to your own player. Per-word timing keeps them in sync.
Diarization tags each voice; click any line to jump to that second. Search a name or phrase and every match returns with a timestamp.
DOCX, TXT, SRT, VTT, and JSON — all included at the base price. Use the transcript in a doc, a video, or a script.
Pricing
A short clip is free. A 1-hour video runs about $2. Prorated to the second; no per-seat licensing; no monthly minimum.
FAQ
Drop the video file above. Speaker-labeled transcript with timestamps + SRT/VTT returns in about a minute per 30 minutes. Preview with no signup; a free account (60 minutes included) unlocks the full text.
No. Upload the video as-is; we handle the audio track. No converting to MP3 or pulling the audio out.
MP4, MOV, MKV, AVI, WebM, FLV, and most containers, plus audio like MP3, M4A, WAV, FLAC.
Yes. Export SRT and VTT for captions, plus DOCX, TXT, and JSON — all at the base price.
Yes. Private Whisper, no third-party service, no training on uploads. TLS 1.3 in transit, AES-256 at rest, delete anytime.
100+ languages. Transcribe in the source language or export an English translation track for subtitles.
Instant preview, no signup, no card. Any format. A free account includes 60 minutes.