Transcript chapter maker
Create timestamped sections from a local speech transcript.
Transcript chapter maker
Drop your files here
or choose files from your device
Kuidas kasutada Transcript chapter maker
The transcript chapter maker transcribes a recording with Whisper in the browser and lists the transcript as numbered sections, each with its start and end time in seconds. Results download as notes.md in Markdown along with a plain transcript.txt. You can set the language or leave it blank for detection, and transcribe from 1 to 120 seconds.
- Choose a source file. If the tool accepts multiple files, arrange them in the order you want.
- Set language code (blank = detect), maximum seconds.
- Run transcript chapter maker, review the output, then use the available copy or download controls.
Mida see tööriist toetab
Local Whisper transcription produces timestamped transcript sections. Meeting action candidates use phrase matching; these are extractive drafts, not a generated summary. Review transcription errors.
- Language code (blank = detect)
- Set this value for your task.
- Maximum seconds
- Range: 1 to 120
Piirangud ja töötlemine
Image inputs: up to 32 megapixels, batches up to 10 images. Audio/video uploads: 50 MB; transcription: 120 seconds. Edited videos: 20 seconds, 4 fps and 640 pixels wide. Translation: English/Spanish, 30,000 characters; subtitles: 200 cues. Neural speech: 1,000 English characters. Model downloads and memory requirements vary by device.
Näite lähteandmed
A useful tool makes everyday work easier. Review the results before sharing.
Korduma kippuvad küsimused
Are the chapters based on topics in the audio?
No. Sections follow the timestamped segments Whisper produces, not topic changes. The tool states they are extractive transcript sections rather than generated summaries or semantic chapter boundaries.
What files does the transcript chapter maker produce?
Two downloads: notes.md, a Markdown document with a numbered heading and time range for each section, and transcript.txt containing the full transcript text without timestamps.
How do I turn the sections into YouTube chapters?
Each section heading shows its start time in seconds, such as 12.5. Convert those values to minutes and seconds and choose the sections that mark real topic changes, since the tool does not merge segments by subject.
Where is my input processed?
Source files and text stay in this browser. The first run downloads public models from Hugging Face and local runtime assets from the site. Models may remain in the browser cache. No source upload to Vercel, Supabase or a conversion service is required.
What are the input limits?
Image inputs: up to 32 megapixels, batches up to 10 images. Audio/video uploads: 50 MB; transcription: 120 seconds. Edited videos: 20 seconds, 4 fps and 640 pixels wide. Translation: English/Spanish, 30,000 characters; subtitles: 200 cues. Neural speech: 1,000 English characters. Model downloads and memory requirements vary by device.