All tasks / Tools
NVIDIA NeMo Speech
NVIDIA's open-source toolkit to train, fine-tune and run speech models such as Parakeet, Canary and Magpie.
- NVIDIA
- Local only
- Free, open source
Where it ranks
- CText to speechLocal servers & APIs · Local · via Magpie-Multilingual 357M (Feb 2026)
- BTranscriptionEngines & APIs · Local · via Canary-Qwen-2.5B
Tools without a benchmark of their own inherit the tier of the best model they offer.
Facts
- Vendor
- NVIDIA
- Approach
- Local servers & APIs, Engines & APIs
- Where it runs
- Runs only on your own hardware
- Interface
- API, Command line
- Skill level
- Advanced: command line, node graphs or self-hosting
- Price
- Free, open source
- Pricing notes
- Free and open source.
- Source code
- Open source (Apache-2.0)
- GitHub stars
- 18.6k (19 Oct 2026)
- Last verified
- 19 Oct 2026
Price from github.com, 19 Oct 2026.
Models it gives you
- BCanary-Qwen-2.5BNVIDIA · open weights
- BParakeet TDT 0.6B v3NVIDIA · open weights
- CNemotron 3.5 ASR Streaming 0.6BNVIDIA · open weights
- CMagpie-Multilingual 357M (Feb 2026)NVIDIA · open weights