The catalog stores audio as true, false, or null. Native audio is the true case: dialogue, effects, and ambience come out of the same generate as the picture. A silent row is the other case. You get an MP4 with no soundtrack, or with a track that is empty. That is not a defect. It is the older, still-common pipeline: generate picture, then write sound.
Text-to-speech and voiceover are how speech gets onto that picture. Lipsync is how a mouth in frame gets matched to a track you already have. Replacing baked native audio later is an edit; adding audio to a silent row is the intended path. A brief that says 'she says the line' on a silent row will give you a mouth flap and no voice, or a mouth that never moved, depending on the model. Read the row before you write the line into the prompt.
Silent turbo rows are often the cheaper draft. Lock composition and motion there, then either upscale, move to a native-audio row, or attach a designed mix. Sound-on strategy still wants a reward when the viewer unmutes; a silent row just means you author that reward on the timeline instead of in the generate. Mute-autoplay feeds will not care which path you took if the burn-in carries the claim.
In practice
- Check the row's audio flag before you prompt spoken lines. False or null means you will add the read afterwards.
- Generate the voice as its own job — TTS or a clone — then attach it, or lipsync if a mouth must match.
- Do not treat a silent export as a failed native-audio run. Many rows never offered sound.
The mistake to avoid
Prompting dialogue on a silent row and blaming the model when the clip has no voice. The catalog already said the soundtrack was yours.
Where you will run into it
- Add a Voiceover to a Video — Type the script. Get a narrated video back.
- Replace the Audio in a Video — Mute the original. Put your own sound in its place.
- AI Video Generator — Text-to-video, image-to-video, and story chaining in one studio.
- AI Text to Speech — One script, several engines, one bill in credits.
Related terms
Native audio
Native audio meaning: a video model that generates soundtrack (dialogue, effects, ambience) in the same pass as the picture.
Text-to-speech
Text-to-speech converts written text into spoken audio using a synthetic voice you choose before generating.
Voiceover
A voiceover is a spoken track laid under picture, rather than lipsync that drives a mouth or a caption track that visualises speech.
Temporal consistency
Temporal consistency is how well a generated clip keeps things the same from one frame to the next, with no flicker, shimmer or drifting detail.
Character consistency
Character consistency meaning: whether the same person, mascot, or product still looks like itself across separate generations.
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync, in your browser or on your phone.
Free on the web and on iPhone, one account.