Text-to-speech
VibeVoice-Realtime 0.5B requirements, license & speed
By Microsoft · released 2025-12-04 · 0.5B LLM (1.02B total in safetensors) parameters
Commercial useYes
Min memoryNot stated
Runs on CPUUnknown
StreamingYes
Key facts
- License
- mit source
- Commercial use
- Yes sourceMIT, but Microsoft does not recommend commercial/real-world use without further testing; card lists prohibited uses
- Parameters
- 0.5B LLM (1.02B total in safetensors) source
- Minimum memory
- Not stated by source
- Runs on CPU
- Unknown
- Streaming
- Yes sourceStreaming text input
- Voice cloning
- Unknown
- Languages
- English (+ experimental voices in 9 more languages) source
- Released
- 2025-12-04 sourceHugging Face repo creation date (proxy for release date)
- Gated on HF
- No
Measured speed & memory
Benchmark pending. We haven't measured VibeVoice-Realtime 0.5B yet. Planned targets: Raspberry Pi 5, CPU-only x86, Apple Silicon Mac and consumer GPUs. Get notified.
Accuracy
We don't run accuracy evals. For quality and intelligibility, check the Hugging Face Open TTS Leaderboard.
Similar TTS models
Spotted an error? Report it. Every fact links to the model card or repo it came from.