VibeVoice Realtime 0.5B is a lightweight real-time text-to-speech model from Microsoft with streaming text input and long-form speech generation, producing the first audible speech in about 300 ms. It encodes incoming text chunks while continuing diffusion-based acoustic generation, using only an acoustic tokenizer at 7.5 Hz. It is built primarily for English, with nine more languages available to try: German, French, Italian, Japanese, Korean, Dutch, Polish, Portuguese and Spanish.
$0.01
How long a request takes over every route we serve it from: from sending it to the complete result.
Share of requests served without a server error. Client errors (4xx) do not count.
No optional parameters beyond the standard request.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Characters of text spoken per day on NagaAI, counted since November 2026.
VibeVoice Realtime 0.5B is a lightweight real-time text-to-speech model from Microsoft with streaming text input and long-form speech generation, producing the first audible speech in about 300 ms.
On NagaAI, VibeVoice Realtime 0.5B costs about $0.01 per 1k chars. You pay only for what you use, with no subscription.
It takes text as input and returns speech.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI SDK pointed at NagaAI. The API section on this page has a ready example.
Not enough activity data to display a chart
Not enough data yet