VibeVoice-Realtime-0.5B

Model facts

Hub id

microsoft/VibeVoice-Realtime-0.5B

Likes

1,304

Downloads (last 30 days)

292,253

Task

Text to speech

Library

transformers

Parameters

1.02B (1,017,626,722)

License

MIT (mit)

Access

Open download

Author

microsoft · Organization

Languages

en

Created

Dec 4, 2025

Last modified

Dec 12, 2025

Base model

• Fine-tuned from Qwen/Qwen2.5-0.5B

Rank #251 of 4,320 models in AI on Hugging Face, by likes. Data from the Hugging Face Hub API, fetched Oct 18, 2026. Likes measure popularity, not quality or safety. Downloads are for the last 30 days, as the Hub reports them; counts change daily. A listing is not an endorsement. How this list is made

More models from microsoft

• 48

  Rank 48: microsoft/phi-2

  3,527 likes481,518 downloads in the last 30 daysText generation2.78B parametersMIT

• 86

  Rank 86: microsoft/VibeVoice-1.5B

  2,501 likes552,365 downloads in the last 30 daysText to speech2.7B parametersMIT

• 102

  Rank 102: microsoft/phi-4

  2,326 likes359,004 downloads in the last 30 daysText generation14.7B parametersMIT

• 132

  Rank 132: microsoft/Florence-2-large

  1,876 likes361,760 downloads in the last 30 daysImage and text to text777M parametersMIT

• 159

  Rank 159: microsoft/OmniParser

  1,718 likes944 downloads in the last 30 daysImage and text to textMIT

• 161

  Rank 161: microsoft/Phi-3-mini-128k-instruct

  1,708 likes211,405 downloads in the last 30 daysText generation3.82B parametersMIT