Try MiniMax FastH3 V2 from Fastvideo →
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Audio & SpeechActive

VibeVoice-Realtime

bymicrosoft

VibeVoice-Realtime is a lightweight real‑time text-to-speech model supporting streaming text input and robust long-form speech generation.

Text to SpeechFast Inference
Model ID
VibeVoice-Realtime
Provider
microsoft
Updated
1770489015
Support Wiro on G2
wiro playground—microsoft/VibeVoice-Realtime
Reset to defaults

The prompt to generate audio from.

Sample outputs
Updated 1770489015

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).

API quick start

Run VibeVoice-Realtime with a single API call.

POST https://api.wiro.ai/v1/Run/microsoft/vibevoice-realtime
{
  "prompt": "Wiro AI provides easy-to-integrate AI API…",
  "speakerName": "en-carter_man",
  "scale": 1.5
}
curl
curl -X POST "https://api.wiro.ai/v1/Run/microsoft/vibevoice-realtime" \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_WIRO_API_KEY" \
  --data-binary @- <<'JSON'
{
  "prompt": "Wiro AI provides easy-to-integrate AI API…",
  "speakerName": "en-carter_man",
  "scale": 1.5
}
JSON
View full API docs