Skip to content
Thryve

Thryve Scribe

Transcribe audio and video to accurate text. Run it locally in your browser for full privacy, or choose fast cloud transcription where audio is processed in memory and never stored.

License

Privacy

Processed entirely on your device

Local transcription never leaves your device. Cloud is opt-in.

Thryve Scribe turns audio and video into accurate text using Whisper. Local transcription runs entirely in your browser and never leaves your device; an opt-in fast cloud mode sends a recording to our server only when you want extra speed or your device is struggling. Export as TXT, SRT, VTT, or PDF.

How Thryve Scribe works

  1. 1

    Drop your audio or video

    Works with MP3, WAV, M4A, AAC, OGG, FLAC, MP4, MOV, WebM, and more, up to 5 GB per file and up to 50 files at once.

  2. 2

    Set language, quality, and mode

    Auto-detect the spoken language from Whisper’s full 99-language set, or set it yourself. Pick a local quality tier (Fast, Balanced, Accurate), or switch to cloud mode for a speed boost on longer recordings (subscription required).

  3. 3

    Let it transcribe

    Local mode downloads a Whisper model once and runs entirely on your device from then on. Cloud mode splits long recordings into chunks behind the scenes and stitches the results back together.

  4. 4

    Export the transcript

    Download plain text, a formatted PDF, or timestamped SRT/VTT captions ready for a video editor, as a single file or a zip for a batch.

Why teams choose Thryve Scribe

Local by default

Whisper runs in your browser via WebGPU or WASM. Your recordings stay on your device unless you deliberately switch to cloud mode.

Cloud speed, when you want it

Send a recording to our server for faster, hosted transcription on slower devices. Long files are chunked and stitched back together automatically.

Four export formats

TXT for plain text, PDF for a shareable document, and SRT or VTT for timestamped captions.

Multiple ways to access

3 free transcripts a day to start. Thryve Scribe Local ($5/mo) unlocks unlimited local transcripts; Thryve Scribe Cloud ($20/mo) adds unlimited fast cloud transcription. Scribe has its own plans and is not included in Thryve OS Pro.

What it detects and edits

Automatically detects

  • Language auto-detection
  • Timestamped segments for captions

Manual controls

  • Pick a specific spoken language
  • Choose local vs. cloud transcription
  • Export TXT, PDF, SRT, or VTT

Perfect for

StudentsJournalistsPodcastersResearchersMeeting note-takersContent creators captioning video

How it compares

 Thryve ScribeTypical online transcription tool
Local, on-device option
Upload required by default
Caption export (SRT/VTT)Sometimes

Frequently asked questions

Does Thryve Scribe upload my recording?

Not by default. Local transcription runs entirely in your browser via Whisper. Audio only reaches our server if you deliberately switch that recording to cloud mode.

What is cloud mode for?

Cloud mode transcribes on our server instead of your browser, which helps on slower devices or long recordings. It requires a Thryve Scribe Cloud subscription, and long files are automatically split into chunks and stitched back into one transcript.

What formats can I export?

Plain text (TXT), a formatted PDF, and timestamped SRT or VTT caption files for a video editor.

Is Thryve Scribe free to use?

You get 3 free transcripts a day. Thryve Scribe Local ($5/mo) removes that limit for local transcription; Thryve Scribe Cloud ($20/mo) also unlocks unlimited fast cloud transcription. Scribe has its own plans and is not included in Thryve OS Pro.

How large a file can I transcribe?

Up to 5 GB per file, up to 50 files at once. Local transcription has no fixed size cap beyond your device’s memory and time; cloud transcription automatically splits longer files into chunks and stitches them back together.