Conversational voice AI agents

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

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

Official Python SDK for Deepgram.

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

Official JavaScript SDK for Deepgram.

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.

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.

Create videos programmatically with Claude Code and Remotion

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

Community Rust SDK for Deepgram.

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.

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

Official .NET SDK for Deepgram.

A Python script that generates subtitles and renders them onto the video.

Demo for Deepgram Voice Agent API

Generate your audio transcripts with ease.

Get started using Deepgram's Live Transcription with this Flask demo app

Code snippets showing how to record I2S audio and store as .wav file on ESP32 with SD card, how to transcribe pre-recorded audio via Deepgram SpeechToText (STT) API, how to generate audio from text via TextToSpeech (TTS) API from OpenAI a/o SpeechGen a/o Google TTS. Triggering ESP32 actions via Voice.

Talkmore with Opentypeless. Type with your voice. Anywhere. Talk - Recoding - Polish - Done!

WIP exploration using Twilio Media Streams and Generative AI

Get started using Deepgram's Live Transcription with this Node demo app

VoiceTyper-Pro is an advanced speech-to-text dictation tool built with Python and powered by the Deepgram API. Alternative to Mac Whisper, Voice Access, and other voice typing tools.

A lightweight SIP-to-AI voice bridge connecting telephony calls to AI voice agents (OpenAI Realtime GA, Deepgram). Built with asyncio.

Interview-Assistant is a real-time transcription and answer assistant tool. It transcribes system audio in real-time using Deepgram and provides a text box. Additionally, it uses OpenAI's GPT for generating suggested responses based on the transcription, allowing custom prompts and media uploads like images or PDFs.

openduplex uses speech-to-text, artificial intelligence and text-to-speech, to call businesses and make appointments for you

Sample code for live ASR with Node.js and Deepgram