Picovoice/cobra

On-device voice activity detection (VAD) powered by deep learning

48
/ 100
Emerging

This helps identify when someone is speaking in an audio stream, making it easier to process voice recordings efficiently. It takes live microphone input or audio files and outputs a probability score indicating the presence of speech. Anyone building voice-enabled applications, like call center analytics, voice assistants, or smart home devices, would use this to manage audio input.

248 stars.

Use this if you need to accurately detect voice activity in real-time or from recorded audio on various devices without relying on cloud services.

Not ideal if you need to transcribe speech into text, identify specific speakers, or understand the content of the conversation.

voice-enabled-apps audio-processing speech-detection on-device-AI real-time-audio
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

248

Forks

17

Language

Python

License

Apache-2.0

Last pushed

Mar 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Picovoice/cobra"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.