real-time-speech

Dessa is a full-duplex speech-to-speech model that can run on consumer GPUs, being described as a GPT-3 moment for speech.

Google Devs share a thread showcasing experimental builds and tools created by their teams using Gemini models, ranging from interactive 3D worlds to real-time speech applications.

Inworld has acquired the real-time voice-agent platform Ultravox and migrated its built-in voices to Realtime TTS-2, which supports natural-language inline instructions for controlling pace, tone, and emotion during a conversation.