Skip to content

chloepilonv/podcast-voice-agent

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Podcast Voice Agent

AI guest for live podcast interviews. Uses OpenAI Realtime API for speech understanding and ElevenLabs for voice synthesis.

Hosts (Riverside mics)
        ↓
Browser (WebRTC mic capture)
        ↓
OpenAI Realtime (speech → text response)
        ↓
ElevenLabs TTS (cloned voice)
        ↓
BlackHole → Riverside records AI guest track

Setup

npm install
cp .env.example .env   # add your API keys
node server.mjs        # http://localhost:3000

.env

OPENAI_API_KEY=sk-...
ELEVENLABS_API_KEY=...
ELEVEN_VOICE_ID=...
MODEL=gpt-4o-realtime-preview

Riverside + Mac audio routing

  1. Install BlackHole 2ch
  2. Open Audio MIDI Setup → create Multi-Output Device (Speakers + BlackHole)
  3. System Output → Multi-Output Device
  4. Riverside AI mic input → BlackHole

About

Built an Ada Lovelace agent to interact with in a podcast

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors