Crossing the uncanny valley of conversational voice
sesame.comSaved by shashaank and
Crossing the uncanny valley of conversational voice
Multimodal AI models (vision, language, action) enable robotics to understand and act on language commands, creating new human-robot interfaces.
TRANSCRIPT
What is the state of the art with the vision, language, action models today? So a generalized system, a box, a machine that can observe the world with a camera, and then I can use language, I can use text or speech to tell it I want you to do it and then it knows how to act physically to do something in the physical world for me. Yeah, that's
... See moreGoogle presents AudioPaLM: A Large Language Model That Can Speak and Listen
paper page: https://t.co/ZXFa4sRK03
introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and... See more
AKx.com@swarajbachu voice in --> deepgram stt --> gpt4o llm --> elevenlabs tts --> voice out
enabled by webrtc transport @trydaily
built with @pipecat_ai
Aman Ibrahimx.com