Registry / ai-ml / realtimestt

realtimestt

JSON →
library1.0.2pypypiunverified

RealTimeSTT is a fast Voice Activity Detection (VAD) and real-time speech-to-text transcription system for Python 3.11+. It uses Silero VAD for voice activity detection and multiple backends (e.g., faster-whisper) for transcription. Current version: 1.0.2 (Nov 2024). Release cadence is irregular.

pip install realtimestt
INSTALL
IMPORT
SIG · REALTIMESTT
R
realtimestt
ai-mlpythonv1.0.2
harness data pending
Install & Compatibility
Where this runs

No compatibility data collected yet for this library.

Code
Verified usage

Verified import paths — ran on the pinned version, not inferred.

RealtimeSTT
from realtimestt import RealtimeSTT
from realtimestt.realtimestt import RealtimeSTT
Common mistake: trying to import from a nested module instead of top-level package.

Minimal example that captures microphone audio and returns transcribed text.

from realtimestt import RealtimeSTT stt = RealtimeSTT() print("Listening... say something") text = stt.transcribe() print(f"You said: {text}")
Debug
Known issues
breakingPython 3.11+ only. Versions older than 3.11 will raise import errors.
fix
Upgrade to Python 3.11+.
affects: 1.0.0+
gotchaMicrophone access: On Linux, you may need to install portaudio or pyaudio system dependencies. On Windows, the default microphone may not be selected.
fix
Install system audio libraries: sudo apt-get install portaudio19-dev (Linux). Use pyaudio.pa.get_default_input_device_info() to check.
affects: all
gotchaModel download on first run: Silero VAD model is downloaded automatically to ~/.cache/torch/hub. Ensure network access and sufficient disk space.
fix
No fix needed, but pre-download by running a dummy import.
affects: all
Upgrade
Version history
1.0.2latest on PyPI · released May 31, 2026
Audit
Dependencies
torchoptionalRequired for Silero VAD models
Agent activity
8 hits · last 30 days
node
6
OpenAI (training)
1
Resources
realtimestt — pip install realtimestt · libregistry