Picovoice/cheetah
On-device streaming speech-to-text engine powered by deep learning
This tool helps convert spoken words into text instantly, right on your device, without sending your audio to the cloud. You speak into a microphone, and the software provides a real-time transcript. It's designed for developers building applications where privacy, speed, and offline functionality for speech-to-text are critical.
661 stars. Actively maintained with 34 commits in the last 30 days.
Use this if you are a developer creating applications that require accurate, real-time speech-to-text conversion directly on user devices for privacy or offline use.
Not ideal if you need to process large batches of pre-recorded audio files or if you require speech-to-text for less common languages not currently supported.
Stars
661
Forks
76
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 18, 2026
Commits (30d)
34
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Picovoice/cheetah"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
PaddlePaddle/PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with...
k2-fsa/sherpa
Speech-to-text server framework with next-gen Kaldi
yeyupiaoling/YeAudio
Python的音频工具
zaigie/FunSpeech
开箱即用的本地私有化部署语音服务，快速搭建FunASR与CosyVoice2/3后端
manyeyes/ManySpeech
AI Speech Solutions for Tasks such as ASR, Vocal Extraction, Accompaniment Extraction, Audio...