FreeRun multilingual speech recognition or translation with an open NVIDIA model.
Audio & Voice
All tools
View more Free 
Free
Access
Free
2
Audio & Voice Checked Aug 6, 2026
Parakeet TDT 0.6B v2
Turn English speech into punctuated text with word timestamps using an NVIDIA open ASR model.
Best for: Builders and researchers who want an open transcription model rather than a subscription-only editor.
What you can do with it
- Transcribe an interview recording
- Create timestamped meeting notes
- Generate captions from spoken audio
- Prototype a local speech-to-text workflow
- Compare an open ASR model on noisy audio
Good to know
- Open NVIDIA model
- Automatic punctuation and capitalization
- Word-level timestamps
- Public demo available
Limitations
- English-focused
- Hardware may be required for local use
- Noise and accents affect accuracy
Other official links
Keep exploring
Similar tools
FreeUse text and optional audio to explore unusual sound generation and transformation.
Audio & Voice
FreeGenerate expressive, multilingual speech from a short voice reference with an open local model.
Audio & Voice