realtimestt

What it is and what it does

RealtimeSTT is a Python library that captures audio from a microphone or external stream, detects when speech is happening using voice activity detection (VAD), and transcribes it to text. It's designed for applications like voice assistants, dictation tools, and streaming servers that need to turn speech into text with minimal code. The library supports multiple transcription backends (faster-whisper, OpenAI Whisper, Silero, and others) via optional extras, so you install only what you need. It includes WebRTC VAD by default and can optionally use Silero VAD for better accuracy, plus optional wake-word detection through Porcupine or OpenWakeWord.

The core package is lightweight, but it depends on PyAudio, torch, torchaudio, scipy, websockets, and other audio libraries. Installation requires system-level PortAudio headers on Linux and macOS. Python 3.11 or newer is required. The package uses multiprocessing for model work, which means you must guard your main code with `if __name__ == "__main__":` on Windows. You can feed audio from files, streams, or websockets by setting `use_microphone=False` and calling `feed_audio()` with PCM chunks.

Use it for:

• Build a voice assistant that listens for a wake word, then transcribes commands in real-time with minimal latency.
• Create a dictation tool that continuously records speech and processes transcripts asynchronously via callbacks.
• Stream audio from a websocket or external source and transcribe it without touching the local microphone.
• Prototype a speech-to-text pipeline where you can swap transcription engines (faster-whisper, Kroko, Silero) without changing application code.
• Detect ambient noise levels and voice activity to trigger recording or filtering in audio processing pipelines.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

RealtimeSTT converts speech from microphone or external audio streams into text using voice activity detection and pluggable transcription engines like faster-whisper, with optional wake-word activation.

Yes. RealtimeSTT is actively maintained, has no known vulnerabilities, and offers a clean API for real-time speech-to-text with flexible backend selection. The permissive MIT license and low install friction (pure wheel, optional extras) make it low-risk. The main gotchas are the system PortAudio dependency and Python 3.11+ requirement; if your environment meets those, it's a solid choice for local speech recognition without cloud APIs.

Install

realtimestt on PyPI

pip install realtimestt

uv add realtimestt

poetry add realtimestt

Installing realtimestt

Before you install

Low install friction; pure Python wheel. Requires system PortAudio headers (apt-get on Linux, brew on macOS) and Python 3.11+. Nine runtime dependencies including torch, torchaudio, and PyAudio; optional extras let you choose transcription backends. Actively maintained with recent commits and 10055 GitHub stars.

License in practice

MIT license is permissive; you can use, modify, and distribute this package freely in commercial or private projects with minimal restrictions.

Quickstart

pip install "realtimestt[faster-whisper]"

from RealtimeSTT import AudioToTextRecorder

if __name__ == "__main__":
    with AudioToTextRecorder() as recorder:
        print("Speak now")
        print(recorder.text())

Requires Python 3.11+, system PortAudio headers (apt-get install portaudio19-dev on Linux, brew install portaudio on macOS), and torch/torchaudio installed via the extras.

Verify before relying

• Whether the package's multiprocessing implementation works reliably across all platforms and Python patch versions.
• Real-world latency and accuracy benchmarks compared to other local speech-to-text solutions.
• Stability and completeness of less-common backend integrations (Kroko, Omnilingual, Parakeet).

Package facts

Evidence: realtimestt-1.0.2-py3-none-any.whl

Keywords: real-time, audio, transcription, speech-to-text, voice-activity-detection, VAD, real-time-transcription, ambient-noise-detection, microphone-input, faster_whisper, speech-recognition, voice-assistants, audio-processing, buffered-transcription, pyaudio, ambient-noise-level, voice-deactivity

Tags

More Artificial Intelligence packages