Media to Script — paste image / video / audio, get a human-readable narrative

gemini-textmarlin-videowizpergemini-ttschatterbox-tts

Output

gemini-text (vision) for images

marlin-video for short videos

wizper for audio transcription

gemini-text narrative rewrite

6 reading levels, 5 output formats

Chains into talking-avatar.md

Time

matches source (single-pass, finite media)

Budget

$0.01–$0.50 per source, plus optional voice render

Reliability

4.0

Customize this playbook

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

Project

Name

Source

Image URL

Video URL

or any video URL; yt-dlp handles fetch

Audio URL

File

uploaded file

Target language

any gemini-text supported language

Reading level

Target length

"30 seconds" | "1 minute" | "5 minutes" | "as long as needed"

Tone

warm-curious | reverent | clinical | playful | journalistic

Output format

script (default) | bulleted-notes | dialogue (multi-speaker) | poem

Project slug

Also synthesize audio

Also make talking avatar

RUNNER

$npm install -g @livepeer/runner