Transcription
Parakeet TDT v3
25 mostly European languages with auto-detect. Fast even on CPU.
- NVIDIABy
- 25Languages
- ~1.2 GBDownload
Can do
- Word timestampsYes. YesTiming for each word, good enough to dub against.
- Speaker labelsNo. NoSays who is speaking.
- Live dictationNo. NoStreams text as you speak.
Languages
25languages
Full list on the model card Runs on
NVIDIA NeMo
isolatedNVIDIA NeMoPyTorchCUDACPUNeeds its own separate Python environment.
Engine docMLX
MLXApple SiliconRuns on the Apple Silicon GPU, about 1.2 GB.
Engine doc
Hardware
| Engine | CUDA | ROCm | Intel Arc | Apple Silicon | Vulkan | NPU | CPU |
|---|---|---|---|---|---|---|---|
| NVIDIA NeMo | Supported | Not supported | Not supported | Not supported | Not supported | Not supported | Supported |
| MLX | Not supported | Not supported | Not supported | Supported | Not supported | Not supported | Not supported |
Supported Needs a build Experimental
Licence
- Terms
- Not stated in the app's docs. Check the model card before commercial use.
VoiceStudio is AGPL-3.0 and doesn't relicense model weights. Licence guide
Related
From the VoiceStudio app at 0834c8b. 27 models listed.