WhisperLive and whisper_mic

These are competitors offering alternative approaches to real-time speech recognition with Whisper: WhisperLive provides a streaming implementation with lower latency, while whisper_mic offers a simpler microphone interface to the standard Whisper model.

WhisperLive
68
Established
whisper_mic
51
Established
Maintenance 20/25
Adoption 10/25
Maturity 16/25
Community 22/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 25/25
Stars: 3,894
Forks: 536
Downloads:
Commits (30d): 13
Language: Python
License: MIT
Stars: 785
Forks: 170
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
Stale 6m No Package No Dependents

About WhisperLive

collabora/WhisperLive

A nearly-live implementation of OpenAI's Whisper.

Supports multiple inference backends (Faster-Whisper, TensorRT-LLM, and OpenVINO) for optimized performance across different hardware, with pluggable model sizes and a client-server architecture for concurrent transcription. Features Voice Activity Detection, real-time translation between any languages, and OpenAI-compatible REST API endpoints alongside native WebSocket streaming for low-latency audio input from microphones or files.

About whisper_mic

mallorbc/whisper_mic

Project that allows one to use a microphone with OpenAI whisper.

Provides real-time speech-to-speech transcription through a CLI tool and Python API, with configurable model sizes (tiny to large) supporting both multilingual and English-only variants. Integrates with system microphone input via PortAudio and can operate in continuous loop mode for live dictation to active text fields. Designed as a lightweight wrapper around OpenAI's Whisper, enabling straightforward integration into other Python projects through the `listen()` method.

Scores updated daily from GitHub, PyPI, and npm data. How scores work