Microsoft’s VibeVoice is an open-source text-to-speech model for podcast-length, multi-speaker audio that captures the ...

Microsoft has launched VibeVoice, a new open-source AI model capable of generating up to 90 minutes of multi-speaker audio ...

OpenAI's Realtime API is now generally available, featuring the new gpt-realtime model for more natural voice agents at a 20% lower cost for developers.

Creating voice agents just got a whole lot easier, thanks to the OpenAI's latest speech-to-speech model, GPT-Realtime.

Discover OpenAI's GPT-Realtime API, the AI that makes voice interactions human-like, multilingual, and emotionally intelligent. Text-to-speech ...