microsoft / text-to-speech updated 7 months ago

VibeVoice-Realtime-0.5B

Name: VibeVoice-Realtime-0.5B
Author: microsoft

VibeVoice-Realtime is a lightweight real‑time text-to-speech model supporting streaming text input and robust long-form speech generation. It can be used to build realtime TTS services, narrate live data streams, and let different LLMs start speaking from their very first tokens (plug in your preferred model) long before a full answer is generated. It produces initial audible speech in ~300 ms (hardware dependent).

Params

1.0 B

Context

—

Downloads 30d

657 K

Likes

1,263

Commercial use: allowed mit Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

662 K650 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	2.0 GB	2.9 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: VibeVoiceStreamingForConditionalGenerationInference
Parameters: 1.0 B
Tensor type: BF16
Licence: mit
First seen on the Hub: 2025-12-04
Base model: Qwen2.5-0.5B
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base Qwen2.5-0.5B Qwen 2.6 M

Compare with

Kokoro-82M 12.0 M XTTS-v2 9.2 M chatterbox 2.5 M Qwen3-TTS-12Hz-1.7B-CustomVoice 2.3 M Qwen3-TTS-12Hz-0.6B-CustomVoice 1.6 M Kokoro-82M-v1.0-ONNX 1.4 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB