Audio
silero-vad
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
★ 10.3k starsMIT
View guide →// audio · Picovoice/cheetah
cheetah
cheetah is an open-source audio project by Picovoice (Picovoice/cheetah on GitHub). It has 670 GitHub stars and 77 forks, is released under the Apache-2.0 license, and was last updated on GitHub on 2 October 2026.
On-device streaming speech-to-text engine for real-time apps.
💎 Hidden gem★ 670 stars⑂ 77 forksApache-2.0updated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- Picovoice/cheetah
- GitHub stars
- 670
- Forks
- 77
- License
- Apache-2.0
- Last updated on GitHub
- 2 October 2026
- Category
- Audio
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- Official site
// how it works
How it works
- Pick your platform
Choose the SDK for your target device.
- Add the engine
Integrate the on-device STT library.
- Stream audio in
Feed live audio and receive transcripts in real time.
- Ship your feature
Live captions, commands, or dictation go live.
// features
Why people love it
On-device STT
Recognition happens locally — no audio leaves the device.
Streaming engine
Real-time transcripts as speech happens.
Deep learning core
Neural models tuned for accuracy and speed.
Cross-platform SDKs
Integrates across mobile, desktop, and embedded.
Low latency
Built for responsive, live transcription features.
Apache-2.0 license
Commercial-friendly open-source terms.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/Picovoice/cheetah.git cd cheetah - Step 2 — Check the README
Every project documents its own setup; start with install requirements.
cat README.md | head -60 - Step 3 — Run it
Follow the project's launch command — Docker, pip, npm, or a binary release.
# see README for the exact launch command
// use cases
What you can build
- Add live captions to a video app.
- Build voice commands into an IoT device.
- Transcribe calls in real time.
- Prototype on-device dictation features.
Advertisement
// faq
Questions, answered
Who maintains cheetah?
It is an open-source project at Picovoice/cheetah with 77 forks. Check the repo's contributors and recent commits to see how active maintenance is.
Is cheetah free for commercial use?
Apache 2.0 licensed — commercial use allowed with attribution.
Does it need the internet?
No — it is an on-device engine by design.
Is it streaming or batch?
Streaming — it produces transcripts in real time as speech arrives.
Which platforms can I build for?
Picovoice targets mobile, desktop, and embedded platforms — check the docs.
// keep exploring
Similar tools
Audio
RealtimeSTT
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
★ 10.2k starsMIT
View guide →Audio
silero-models
Silero Models: pre-trained text-to-speech models made embarrassingly simple
★ 6.1k starsCustom
View guide →Audio
MOSS-TTS
MOSS-TTS family: open text-to-speech models for voice cloning, dialogue, voice design, and real-time agents
★ 4.2k starsApache-2.0
View guide →Audio
hifi-gan
GAN vocoder that turns mel-spectrograms into high-fidelity speech audio, fast enough for real-time use.
★ 2.4k starsMIT
View guide →Audio
dictly
On-device speech-to-text for macOS.
★ 51 starsMIT
View guide →// alternatives
Alternatives in Audio
The most-starred other Audio projects in the LibreAI catalogue — the realistic shortlist if cheetah is not the right fit.
- MoneyPrinterTurbo★ 128.3k
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
- Whisper★ 109.9k
Robust Speech Recognition via Large-Scale Weak Supervision
- GPT-SoVITS★ 62.3k
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- Real-Time-Voice-Cloning★ 60.2k
Clone a voice from 5 seconds of audio and generate arbitrary speech in real time
- whisper.cpp★ 54.1k
Port of OpenAI's Whisper model in C/C++
// more in audio
More in Audio
Nearby Audio projects in the catalogue, closest in stars to cheetah — keep exploring the shelf either side of it.
- dictionariez★ 674
Double-click any word for definitions, speech, translation, and Anki.
- pindrop★ 628
A macOS menu-bar dictation app powered by local WhisperKit.
- TranscriptionSuite★ 759
Fully local transcription with diarization, for every desktop OS.
- opentypeless★ 582
Open-source AI voice typing: hotkey, speak, get polished text anywhere.
- cboard★ 759
Free AAC communication boards with text-to-speech, in the browser.
- joinly★ 566
Give AI agents a seat in your meetings.
Get cheetah
Free and open — grab the source, star the repo, and start creating.