A fully self-hosted multi-modal service, which includes speech-to-text (STT), large lanaguage model (LLM), and text-to-speech (TTS). Includes the option to use open-source models or fully hosted 3rd party solutions like ElevenLabs, ChatGPT etc.
Like this project
Posted Feb 6, 2024
Multi-modal solution (with STT, LLM, TTS) and Twilio, fully self-hosted, low latency. Deploy it make sales calls, receive customer inquiries to inbound number.