Video
Lip-sync
Lip-sync animates a face so the mouth matches an audio track you supply. It is what turns a still portrait or a silent clip into someone appearing to speak your words.
It is a distinct capability from video generation: the model is conditioned on the audio waveform and drives mouth shapes frame by frame. Tools that offer it generally take a face plus a voice file and return a new clip.
Generating speech inside the shot is a different thing entirely — there the engine invents the performance and the sound together, from the prompt and, on some engines, a voice sample, and nothing is matched to a track you supply.
On eroq
eroq has no lip-sync tool. Engines with sound can render a spoken line as part of the clip — Veo 3.1 renders dialogue, and on Seedance and Hailuo 3 a Character's voice sample rides along — but you cannot lay a separate voice track over an existing clip and have the mouth match. Narration from the voice studio is laid under the picture on the Editor's timeline.
Questions
Can eroq make a character speak my script?
Not with matching mouth movement. You can render the voice from your script in the voice studio and the picture separately, then combine them on the Editor's timeline, and the face will not be synced.
What does Veo 3.1 actually do with dialogue?
It generates the line as part of the shot, voice included, from your prompt. You do not choose the voice and you cannot supply the audio, so it suits incidental speech rather than scripted narration.
Is lip-sync on the roadmap?
We do not publish roadmap promises. What is true today is that no endpoint and no studio control does it.