Script-first
Useful when your content starts as copy and needs to become a face-led video quickly.
This workflow is for users who want a simple path from script to speech-synced video through the same lipsync product path already used on the site, not a graph-building session.
The phase-one version is intentionally compact: script in, voice generation, portrait animation, optional body movement when needed, and output review.
Useful when your content starts as copy and needs to become a face-led video quickly.
A creator can understand the whole flow in seconds: text, voice, portrait, output.
Swap script or audio and rerun the relevant stage without rebuilding the workflow by hand.
The workflow is easier to reuse internally because it reads like a production process, not a graph diagram.
Start from the exact copy the video needs to say.
Turn that script into speech inside the same flow, or bring your own audio if it is already recorded.
Feed the generated or uploaded audio into the lipsync step with your chosen face.
Approve, export, or adjust the script, voice, or motion settings and rerun.
Short script-led talking head videos for outreach or landing page embeds.
Reusable support or onboarding clips based on plain text copy.
Reuse the same portrait with different scripts for different markets.
Take a character or portrait, pair it with a script, and optionally add body movement when the speaker should feel more physically present.
Because the main search intent here is about the exact step order from text to lipsync output.
No. The point is to keep the text-to-voice-to-video path inside one broader product environment.
Yes. The phase-one workflow page is lightweight, but it is designed to map cleanly onto richer multi-step creation later.
No. The default talking-head path stays simpler and more stable. Body movement is an optional upgrade when you want more presence from the speaker.