Conversational voice AI agents

Your own personal voice assistant: Voice to Text to LLM to Speech, displayed in a web interface

Official Python SDK for Deepgram.

End-to-end platform for building voice first multimodal agents

Open-source AI meeting copilot - real-time transcription, echo cancellation, and AI assistance. Captures system audio + mic, cancels echo via WebRTC AEC3, transcribes with Deepgram, and gives you Claude/OpenAI help during meetings. Runs locally on macOS and Windows.

Get started using Deepgram's Live Transcription with this Next.js demo app

Official JavaScript SDK for Deepgram.

Create videos programmatically with Claude Code and Remotion

Real-time speech-to-text caption appliance for a deaf user. Raspberry Pi + 10" touchscreen that transcribes phone calls and room conversation in near real-time.

End-to-end workflow to automatically generate show notes from audio/video transcripts

Official Go SDK for Deepgram.

LLM-based two-way translator for VRChat

AI Voice Assistant: Talk to an AI agent that helps you with event scheduling, contact management, accessing your knowledge base, and web searches using simple voice commands

ESP32-based voice device for chatting with multiple custom AI bots. Recording questions with I2S microphone, transcribing via ElevenLabs or Deepgram STT, creating response with Groq or Open AI LLM. TTS audio output with custom AI voices via I2S & speaker. Supporting ongoing dialogues, calling bots ‘by name’, real-time web search via keyword.

Hold-to-talk voice input for Pi CLI — Deepgram streaming STT with live transcription, voice commands, and cross-platform hold detection

Community Rust SDK for Deepgram.

Turn any SIP call into a realtime AI voice agent (OpenAI Realtime / Deepgram/Gemini Live/xAI Grok Voice)

Real Time AI Voice Assistant using nodejs

A simple discord bot that listens to voice channel and generates a transcript, then assigns tasks and summarises the conversation