mercuryScribe

B tier on Podcast Transcription SoftwareScore 7.0 · #5 of 24

Android app: Not listed
Free plan: Yes
Runs on: Linux, Mac, Web, Windows

mercuryscribe.com

Summary

mercuryScribe is a locally run transcription tool for audio and video, with a browser-based interface for working on transcripts. It uses Faster Whisper to transcribe speech and pyannote models to separate speakers. Users can edit transcripts in a browser, save them as VTT files, and create HTML or DOCX outputs that include speaker names and timestamps. The FAQ says audio, transcripts, and metadata stay off external services, while the required models are obtained from Hugging Face. Users need a Hugging Face access token and must accept the model terms. MAXQDA is supported by default, and custom integrations can be developed. The software is free and open source under the MIT license, with personal, academic, and commercial use allowed. It runs on Linux, macOS, Windows, and the web; installation options include Docker, a Windows package, and a Python package. The maker describes it as built for researchers and also suitable for journalists, podcasters, educators, organizations, accessibility groups, and other professionals.

Who it is for

It suits researchers and other professionals who need to transcribe audio or video, label speakers, and edit transcripts. It may also fit teams seeking local operation and MAXQDA support.

What is good

Free and open source under the MIT license
Edits transcripts in a browser
Exports VTT, HTML, and DOCX
Supports speaker labels and timestamps
Available on Linux, macOS, Windows, and web

What to know first

Requires a Hugging Face access token
Users must accept terms for required models
Compliance suitability depends on implementation

Verdict

mercuryScribe combines local transcription with transcript editing and several export options. Check model access requirements and confirm compliance with your organization's team before use.

mercuryScribe plans and pricing

All plans

Free Free Free and open-source under the MIT license; personal, academic, or commercial use mercuryscribe.com · 3 Oct 2026

Compared on podcast transcription software

Free plan: Yesmercuryscribe.com
Speaker labels: Yesmercuryscribe.com
Transcript editor: Yesmercuryscribe.com
Caption export: Yesmercuryscribe.com

Facts

Product: mercuryScribe is a locally run web interface for transcribing audio and video files.mercuryscribe.com · 3 Oct 2026
Transcription: It uses Faster Whisper to transcribe speech and pyannote models to distinguish speakers.github.com · 3 Oct 2026
Editing: Users can edit transcripts in a browser and save changes to VTT files.github.com · 3 Oct 2026
Output: The tool generates HTML and DOCX files with speaker names and timestamps.github.com · 3 Oct 2026
Privacy: The FAQ says audio, transcripts, and metadata are not sent to external services; models are pulled from Hugging Face.mercuryscribe.com · 3 Oct 2026
Compliance: The FAQ says suitability for HIPAA or GDPR depends on the user's implementation and advises consulting their compliance team.mercuryscribe.com · 3 Oct 2026
Integration: MAXQDA support is the default, and custom integrations can be developed.mercuryscribe.com · 3 Oct 2026
Install options: The maker documents Docker, a Windows package, and Python package installation.mercuryscribe.com · 3 Oct 2026
Model access: Users need a Hugging Face access token and must accept terms for the required models.mercuryscribe.com · 3 Oct 2026
Support: Professional services include installation help, team training, workshops, and private server setup with GPUs.mercuryscribe.com · 3 Oct 2026
Paid services: Enterprise support may include priority support, custom installations, SLAs, and pre-configured solutions; the software itself is free.mercuryscribe.com · 3 Oct 2026
Intended users: The maker describes it as built for researchers and suitable for journalists, podcasters, organizations, educators, accessibility groups, and professionals.mercuryscribe.com · 3 Oct 2026