Seedance v1.5 Pro T2V bills 6 credits with sound on

The published Seedance v1.5 Pro T2V row is 1080p, native audio, 4–12s at 6 credits — a different family page from Seedance 2.5 at 47 credits / 720p / 4–30s.

Two Seedance pages sit next to each other in the catalog. They share a brand. They do not share a meter, a ceiling, or a duration enum. Pick the row the shot actually needs. Do not treat 6 credits as a preview of 47, and do not treat 12 seconds as a preview of 30.

6 credits is the listed 1.5 Pro T2V rate, sound on

Seedance 1.5 Pro Text to Video is ByteDance's professional T2V card: listed 6 credits, max output 1080p, qualities 480p / 720p / 1080p, durations 4s through 12s in one-second steps, aspects 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, auto. Catalog audio is true. The generate_audio control on this family defaults on. A prompt that only names choreography still comes back with a score, a whoosh, or a line.

You are not saving 6 credits by omitting the soundtrack from the prompt. You are paying 6 credits for a track you did not art-direct. Write the sound as part of the motion:

• Count, clap, or bare room.
• One instrument if the move is musical.
• Speech only when a mouth is in frame, and then the exact words.
• "No speech, no music, only the sound of the move" when the shot has no mouth.

Then listen. Native-audio rows fill holes. A silent brief still gets a mix.

The AI video generator is the launcher: name 1.5 Pro when the brief is a 4–12s 1080p take with sound on. Cost is priced per model, shown before you confirm. A bare "make a Seedance clip" may land on 2.5. Open the page you mean.

Pick 480p or 720p when the cut is a draft. Pick 1080p when the plate is the plate. Aspect is a dropdown, including 21:9 and auto. Set it. "Cinematic widescreen" in prose does nothing if the control is still 9:16.

Duration is a hard enum. 4s, 5s, and 6s are the social-length windows most briefs actually need. Stretching a two-second gesture across 12 seconds is how the model pads. Compressing a 12-second phrase into 4s is how it smears. Size the choreography to the second you bought.

Duration and 1080p are a different contract than 2.5

1.5 Pro stops at 12 seconds and at 1080p. That is the listed contract, not a taste ranking. Features on the row are professional, text-to-video, V1.5, dance — motion-first, not a 30-second single-shot hold.

Do not promise a 4K master from 1.5 Pro Text to Video. The quality enum tops out at 1080p. Do not promise a 20-second take. The duration enum tops out at 12s. Do not promise a mute file by leaving sound out of the prompt. generate_audio defaults on.

ByteDance's roster also holds later Seedance generations. Those are different cards, different rates, different duration ceilings. This page is 4s–12s, 1080p, sound on, 6 credits listed. This leftover is the bill next to 2.5.

If the shot has no mouth and you truly want mute, say so, then listen. If the series voice is a clone, do not put a singing face in this generate. Native audio already chose a voice. Keep faces from speaking, or pick TTS and a lipsync row instead of fighting this soundtrack.

Seedance 2.5 is 47 credits, 720p, 4–30 seconds

Seedance 2.5 is the later family page: listed 47 credits, max output 720p, qualities 480p and 720p, durations 4s through 30s, catalog audio true, features named text_to_video, long_form, single_shot, cinematic, audio_sync. One text prompt. One continuous shot. Reasoning about the whole take so motion, lighting, and subject identity stay coherent from first frame to last.

That is not 1.5 Pro with a longer slider. 47 credits is not 6. 720p is not 1080p. 30 seconds is not 12. Audio sync is a tagged job on 2.5; 1.5 Pro's catalog boolean is true and its generate-audio default is on, but the family page is still the 6-credit 1080p card, not the 30-second hold.

Use 2.5 when the brief is a long single pass at 720p. Iterate at 4s or 5s until identity holds, then stretch. Thirty seconds is the identity ceiling, not a default. A five-second hold that keeps the subject is an ad. A thirty-second wander that grows a second face is a reroll.

Do not treat 2.5 as a cheaper 1.5 Pro. It is not cheaper. Do not treat 1.5 Pro as a 720p preview of 2.5. 1.5 Pro's ceiling is 1080p. Open the page you mean.

Stitching three 12-second 1.5 Pro takes to fake a 30-second hold is how identity jumps and how you pay 6 credits three times for a mix you still did not art-direct. If the brief is one continuous 30-second shot, you wanted 2.5. If the brief is a 6-second 1080p beat with sound on, you wanted 1.5 Pro. Do not assemble the wrong family out of the right brand.

Do not invent a folded I2V URL

Seedance 2.5's published catalog URL is /models/seedance-2-5. I2V on that family, when you need it, is image-to-video plus that parent page. Do not invent /models/seedance-2-5-image-to-video. That slug is not a live catalog link in this leftover.

The older Seedance Image to Video row is a different page again: 1080p, 2s–12s, 9 credits, audio null. Do not treat it as 1.5 Pro T2V at 6 credits with sound on, and do not treat it as 2.5 at 47 credits with audio sync. Three pages. Three meters.

1.5 Pro T2V does not require an image. If frame one must be a JPEG you approved, you are not on this 6-credit T2V leftover. You are on the image-to-video tool and a live I2V slug. Do not prompt 1.5 Pro to "match this still" as if a sentence were a plate.

The test is the brief. 4–12s, 1080p, sound on, 6 credits listed: 1.5 Pro T2V. 4–30s, 720p, 47 credits, tagged audio sync: Seedance 2.5. A still as frame one: image-to-video plus the parent, never a folded URL you invented.

FAQ

Does 1.5 Pro still generate audio if I omit sound from the prompt?

Yes. Catalog audio is true, and generate_audio defaults on. A silent prompt still gets a soundtrack you did not choose. Write the room, or write quiet. You still pay the listed 6 credits.

Is 6 credits the same job as 47 credits on Seedance 2.5?

No. 1.5 Pro T2V is 1080p, 4–12s, 6 credits listed. Seedance 2.5 is 720p, 4–30s, 47 credits listed, with audio_sync and a single-shot hold. Same brand. Different family page.

Can I open /models/seedance-2-5-image-to-video for a still-to-motion pass?

No. Do not invent that URL. Run image-to-video and the live parent Seedance 2.5. 1.5 Pro T2V is text-only. A still as frame one is a different door.

Is 1.5 Pro a 4K row?

No. Max output resolution is 1080p, with 480p and 720p as quality steps. Do not promise a 4K master from this card. If the brief needs a 30-second single pass, you wanted 2.5, and that ceiling is 720p.