GitLab Transcend - Intelligent orchestration
Mini toolsRealtimeSTT
By KoljaB
RealtimeSTT is a Python speech-to-text library built for live transcription rather than offline batch ASR. The repository says it listens to microphone input, uses WebRTCVAD plus SileroVAD for speech detection and verification, Faster-Whisper for transcription, and Porcupine or OpenWakeWord for optional wake-word activation. It is designed for low-latency voice assistants and similar real-time applications, and also includes a newer client-server setup with AudioToTextRecorderClient and a reworked CLI. One important caveat: the repo clearly states the project is now community-driven and no longer actively maintained by the original author
Audio
Gen 4
Overview
RealtimeSTT is KoljaB’s open-source low-latency speech-to-text library for real-time voice applications. It listens to microphone audio, detects speech activity automatically, supports optional wake-word activation, and performs fast transcription using Faster-Whisper, making it suitable for voice assistants and other live speech interfaces.
Tools using RealtimeSTT
No tools found for this model yet.
Last updated: April 8, 2026
