What is QuentinFuxa/WhisperLiveKit?
QuentinFuxa/WhisperLiveKit is a Python project for speech transcription and automatic captions, with setup instructions in its source repository.
QuentinFuxa/WhisperLiveKit is a Python implementation published in the QuentinFuxa GitHub namespace. The checked project documentation includes setup or usage instructions for a speech-recognition workflow. Its documentation discusses speech transcription, automatic captions, audio recording, translation workflow and speaker labeling. The repository metadata identifies the license as Apache-2.0; review the license text and any separately licensed models before redistribution. A public source repository does not establish production readiness, hosted-service availability or measured transcription quality.
Developers who can inspect installation instructions, dependencies, model requirements and licensing before integrating speech recognition.
Available platform types
Confirm the exact operating system, device and plan requirements with the provider.
Source details
- Repository
- QuentinFuxa/WhisperLiveKit
- Project namespace
- QuentinFuxa
- Main implementation language
- Python
- License metadata
- Apache-2.0
- Default branch
- main
- Last recorded repository push
- 2026-10-01
Key features & workflows
These highlights describe the provider’s public offering. Availability can depend on the selected plan or product version.
Speech transcription
Convert spoken material into text for review and correction.
Automatic captions
Produce text alongside spoken video or audio; check timing and export formats in the app.
Implementation and setup
The repository identifies Python as its main implementation language and documents installation or usage. Dependencies and supported environments should be checked in the current README.
What to check in your trial
Follow the documented setup in an isolated development environment. Check model downloads, hardware needs, licensing, inference costs and a representative audio sample.
- Use a fixed dataset representing the language, accents, audio quality and speaker overlap expected in production. Record the exact model and configuration.
- Measure recognition quality, latency and failure behavior separately. Test reconnects, retries and incomplete audio in the intended API mode.
- Review regions, quotas, retention and request options. Confirm how optional features, channels and long-running jobs affect the bill.
QuentinFuxa/WhisperLiveKit pricing
This entry describes a source-code project rather than a verified hosted pricing plan. Review the license, model terms, hardware requirements and any paid inference or API dependencies in the project documentation.
Compare the complete cost
Calculate cost from the actual billing unit and enabled features. Include streaming versus batch modes, channels, minimum charges, optional analysis, storage and network costs where they apply.
Pricing source checked October 17, 2026. Checkout terms and current offers may change.
Alternatives to QuentinFuxa/WhisperLiveKit
Featured listings and related tools to compare for workflow fit. Placement is not a measured performance ranking.
Common questions
What is QuentinFuxa/WhisperLiveKit used for?
Developers who can inspect installation instructions, dependencies, model requirements and licensing before integrating speech recognition.
Has AI Scribe Review tested QuentinFuxa/WhisperLiveKit?
This is a product profile based on official provider information and editorial selection guidance. A hands-on test, customer rating or measured accuracy score has not been added. Published tests, when available, will appear in the review section below.
Official sources
Project repository and README · github.com↗Product information checked October 17, 2026. Selection guidance is our editorial advice; it is not a report of measured product performance.
QuentinFuxa/WhisperLiveKit review articles
No hands-on review has been published for this product yet.
Visit the review desk →