NVIDIA / NeMo-Speech.cpp
NeMo-Speech.cpp is a lightweight C++ inference runtime for Speech models
Why this job: topics: text-to-speech, speech-recognition
What it does
NeMo-Speech.cpp is blazing fast and built for real-time streaming. Speech recognition transcribes audio in 160 ms chunks up to 67× faster than real time, and speech synthesis generates speech up to 60× faster than real time with its first audio in under 10 ms. Both stay faster than real time even on a CPU.
Get started
curl -fsSL https://github.com/NVIDIA/NeMo-Speech.cpp/raw/main/scripts/install.sh | sh - Maintenance
- Active
- Last commit 7 days ago
- Stars
- 248
- +17 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- 3 systems
- Mac, Windows, Linux
- Latest version
- v0.3.0
- Released 10 days ago
- Built with
- C++
- 76% of the code
Is it looked after?
- Contributors
- 8
- Last 90 days
- Issues
- 47% closed
- 20 still open
- Pull requests
- 36 merged
- 10 waiting
- Releases
- 4
- 4 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| argmaxinc / argmax-oss-swift | 6,447 | 29 days ago | MIT | No downloads |
| Neywa-Labs / mlx-audio | 8,219 | today | MIT | No downloads |
| sgl-project / sglang-omni | 1,718 | today | Apache-2.0 | Mac |
More: download files, languages, topics and project record
Download files, v0.3.0
- Mac6 files, 1,441 downloads
- Windows8 files, 3,874 downloads
- Linux14 files, 3,415 downloads
Languages
- C++ 76%
- Python 13%
- Cuda 5%
- CMake 2%
Topics
- ggml
- inference
- server
- speech-recognition
- text-to-speech
Project record
- JobSpeech and audio
- StatusFeatured
- Commits36
- Forks54
- Watching2
- Stars in 28 days+72
- CreatedJul 15, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026