RealtimeSTT Low-Latency Speech-to-Text Python Library

RealtimeSTT is a Python library for real-time speech-to-text with advanced voice activity detection, wake word activation, and instant transcription. It combines WebRTC VAD, Silero VAD, and Faster Whisper for production-grade voice input in agent applications.

Installation

Use the upstream install or setup path that matches your environment:

• pip install "RealtimeSTT[faster-whisper]"
• brew install portaudio
• python -m pip install -r example_fastapi_server/requirements.txt

Requirements and caveats from upstream:

• RealtimeSTT is a Python speech-to-text library for applications that need
• python
• python example_fastapi_server/server.py --host 0.0.0.0 --port 8010

Basic usage or getting-started notes:

• bash

• On Linux, install PortAudio headers before installing the package:

• sudo apt-get update

• Source: https://github.com/KoljaB/RealtimeSTT

• Extracted from upstream docs: https://raw.githubusercontent.com/KoljaB/RealtimeSTT/HEAD/README.md

Source

• Agent Skill Exchange