Video

Video Generation

Video starts with one of two complete systems, keeps every decision and source attached, and saves finished media in Assets. Use UGC Studio for a new source-grounded campaign or Clip Studio to turn a long recording into its strong, non-duplicate moments. The direct tools remain available when you want to control one generation yourself.

How to access

Open Create, then choose Video. Requires an active synfluencer.

Studios

• UGC Studio — Guides one campaign through eight visible stages: choose one of eight UGC formats; ground the brief and evidence; set independent presenter, product, and supporting-media routes; generate and review five distinct openings in Hook Lab; approve the exact script and treatment; edit and approve a timed visual storyboard; preview the complete profile-voice narration and a five-second hook pilot; then produce, finish, and check the master. Choose either one continuous presenter take or a selected-model five-second presenter opening followed by generated supporting scenes. Route review shows the supporting-scene count and duration, and Storyboard names the production source of every beat. A presenter pilot uses the selected Avatar IV, LC Avatar, MX Avatar, or Aurora Avatar model and the exact approved five-second narration excerpt, so you review real lip sync instead of an unrelated visual proxy. No text panel is forced onto it. Product visual can explicitly be none, approved real media, or a clearly fictional generated concept.
• Clip Studio — Accepts an authorized 20-second to four-hour video, preserves its audio, maps shots and silence, creates a private zero-data-retention timed transcript, and evaluates complete 20–90 second moments. It removes weak candidates and temporal or semantic duplicates instead of filling a clip quota. You can change the title, move bounded edit handles, choose framing, and switch captions on or off before the approved batch is rendered, normalized, checked, and sent to Review.

The prior UGC Ad, Founder Product Video, Viral Hook, Explainer, Content Director, and VFX / 4K VFX recipes are retained only for admin testing and historical runs. Neither UGC Studio nor Clip Studio calls those recipe graphs. Persona playbooks and Brand systems are managed together in the profile's Persona & brand workspace because their approved versions guide every drafting and media workflow. Voice & knowledge remains their evidence library, Assets remains their output library, and Podcast is not currently available.

Video tools

These direct tools stay visible below the studios for one-off clips. Talking-video choices are labeled by the model you will use, not by the company routing the request.

• Talking video — Generates one presenter video from your script and approved narration. Choose the output shape first: Portrait 9:16 is the default, and Landscape 16:9 is available for horizontal delivery. Then choose the matching reference photo and one maker-labeled model: Heygen Avatar IV, LongCat LC Avatar, Mirage MX Avatar, or Creatify Aurora Avatar. MX can instead use a matching portrait or landscape performance video; the person in that clip remains the visual subject and MX replaces only the original audio. Narration uses the profile's explicitly saved ElevenLabs, Gemini, or xAI catalog voice or private authorized Fish Audio clone. Every paid video action stays disabled until you preview and explicitly approve that exact track.
• Generate motion — Creates a new video from a scene prompt. Pick a model from the dropdown — Veo 3.1 Fast (default), Veo 3.1, Kling v3.0 Pro/Standard, Seedance 2.0/Fast, Grok Imagine Video, or Hailuo 2.3. A reference photo is optional: select one for image-to-video, or leave it off for text-to-video.
• Adapt a video — Transfers motion from an authorized source video to an authorized reference image with Kling 2.6 Pro Motion Control. Model-specific duration, format, and reference limits still apply.

Step-by-step

1. Choose UGC Studio for a new campaign, Clip Studio for a long recording, or a direct Video tool for one-off work.
2. For direct Talking video, choose Portrait 9:16 or Landscape 16:9 first. Select a reference photo—or MX performance video—with the same shape, then choose the talking-video model. For Studio work, provide the approved brief or source media and the exact likeness, claim, voice, and source-rights confirmations that apply.
3. In UGC Studio, choose the UGC format and media route, including continuous presenter or presenter opening plus supporting scenes. Review the disclosed route, select and edit one Hook Lab opening, then approve the exact script and the per-beat production source in the timed storyboard. Listen to the complete narration, then play the full five-second selected-model pilot before full scene production. A faceless format labels this as a narrated visual rather than a lip-sync test. If a supporting-scene result is unavailable, recover the retained request first; one replacement requires a spend confirmation, then finishing resumes automatically.
4. In Clip Studio, review every moment that passed the strength and duplicate gates. Edit only the clips you intend to render; Clip Studio never adds weak filler to reach a promised count.
5. Review the estimated range and maximum spend. Synfluencer does not submit paid steps until you confirm the maximum.
6. Follow each step's live status. Generated UGC support scenes are visual-only working clips until approved narration is added during final assembly; the presenter pilot is different because the selected talking model embeds the approved excerpt for lip sync. Clip Studio preserves and normalizes the original source audio in every finished clip, then blocks delivery if that audio cannot decode or contains no audible signal. You can cancel or retry a failed step without discarding completed work. If an older UGC run already completed its selected-model presenter render, Regenerate pilot can recover the first five seconds without another provider charge.
7. Review the masters or clip batch, proxies, thumbnails, captions, scripts, costs, and model attribution. Send approved work to Review. Confirmed UGC narration is saved under Assets → Audio; finished UGC masters and every approved Clip Studio cut remain in Assets.

Cloned voice

Each synfluencer can have its own cloned voice. Open Edit profile → Speaking voice to record a short sample (read the on-screen teleprompter — three parts, each in a different mood so the clone learns your full range; works on desktop and mobile) or upload an existing audio file. Once a clone exists, the Generate preview box lets you hear the saved clone before using it. In that same section, Primary speaking voice lets you save either a compatible catalog voice or the profile's private authorized clone. There is no second chooser in Create or Video. In the Talking video tool, the narration panel lets you generate the narration, preview it, and explicitly approve it before the Avatar IV, LC Avatar, MX Avatar, or Aurora Avatar action becomes available. If no primary voice is saved, Synfluencer asks you to choose one before it calls a provider. Approved audio is saved to Assets → Audio. Voice IDs are not portable between services; Synfluencer supplies the generated audio only where the selected video model accepts external audio.

Model-specific controls

Avatar IV exposes its model-specific motion prompt and expressiveness controls. LC Avatar, MX Avatar, and Aurora Avatar hide those Avatar IV-only fields. All four models can optionally apply the same local audio finish after rendering. Fish clone previews do not claim an automatic emotion-cue pass; their delivery comes from the authorized clone and the script you review.

Audio upgrades

After generating a video, you can upgrade its audio track. Select from available audio templates, preview the result, and save. Audio upgrades are also available from Assets.