Talking Head

Talking Head Video Generator

Create lip-synced avatar videos from text scripts.

Pipeline

1. Write script — the words your avatar will speak
2. Generate audio — ElevenLabs TTS with your chosen voice
3. Generate video — VEED Fabric 1.0 via Fal API or similar

Prerequisites

1. ElevenLabs API Key — store at ~/.config/elevenlabs/api_key
2. Fal API Key — store at ~/.config/fal/api_key (for video generation)
3. Avatar image — clear, front-facing headshot (512x512+)

Quick Start

EL_KEY=$(cat ~/.config/elevenlabs/api_key)

# List available voices
curl -s "https://api.elevenlabs.io/v1/voices" \
  -H "xi-api-key: $EL_KEY" | python3 -c "
import sys, json
for v in json.load(sys.stdin)['voices'][:20]:
    print(f\"{v['voice_id']}: {v['name']}\")"

# Generate TTS audio
curl -s -X POST "https://api.elevenlabs.io/v1/text-to-speech/VOICE_ID" \
  -H "xi-api-key: $EL_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Your script here", "model_id": "eleven_multilingual_v2"}' \
  --output audio.mp3

# Then use Fal API for video synthesis with the audio