Talking Avatar — document in, talking-avatar video + audio out

gemini-textkrea-2-largegpt-imagegemini-ttschatterbox-ttsinworld-ttslipsyncffmpeg-audio-mix

Output

gemini-text review + speak-out optimize

gpt-image avatar portrait (1024²)

gemini-tts audio (30+ langs)

sync-lipsync/v3 lip-sync

Talking-avatar MP4 (artifact 1)

Standalone audio MP3 (artifact 2)

Multi-speaker mode (optional)

Time

matches source document, typically 30s–5min

Budget

$0.50–$3 per minute of output

Reliability

3.2

Customize this playbook

Fill in the fields below. Your answers are inserted into the complete recipe when you copy it.

Project

Name

Source

Text

URL

File

local file

Source language

for reference; agent auto-detects

Target language

what the avatar speaks

Voice archetype

free-form description

Voice gender

male | female | neutral

Voice age

the voice character's apparent age

Voice pace

measured | conversational | energetic | reverent

Avatar archetype

Avatar setting

Project slug

Output aspect

1:1 (default) | 9:16 (TikTok / Reels) | 16:9 (cinema)

Multi speaker

Audio only also

RUNNER

$npm install -g @livepeer/runner