how to do this, easy mode: 1. flux kontext, upload your image, and prompt the scene (https://t.co/as3Se7Zsgw) 2. Dump it into veo3 with prompts for animations 3. Eleven labs audio to audio with whosever voice you need kontext will maintain consistency reasonably... See more

Google 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

@swarajbachu voice in --> deepgram stt --> gpt4o llm --> elevenlabs tts --> voice out enabled by webrtc transport @trydaily built with @pipecat_ai