Speech-to-text
Parakeet Unified EN 0.6B requirements, license & speed
By NVIDIA · released 2026-04-07 · 600M parameters
Commercial useYes
Min memoryNot stated
Runs on CPUUnknown
StreamingYes
Key facts
- License
- NVIDIA Open Model License source
- Commercial use
- Yes sourceCard: ready for commercial/non-commercial use (NVIDIA Open Model License terms apply)
- Parameters
- 600M source
- Minimum memory
- Not stated by source
- Runs on CPU
- Unknown
- Streaming
- Yes sourceOffline + streaming in one model; latency 160 ms to 2080 ms
- Voice cloning
- n/a (speech-to-text)
- Languages
- en source
- Released
- 2026-04-07 sourceHugging Face repo creation date (proxy for release date)
- Gated on HF
- No
Measured speed & memory
Benchmark pending. We haven't measured Parakeet Unified EN 0.6B yet. Planned targets: CPU (8 vCPU), Apple Silicon Mac, RTX-class consumer GPU and a rented cloud GPU. Get notified.
Similar STT models
Spotted an error? Report it. Every fact links to the model card or repo it came from.