by BytedanceReleased 23 March 2026
Seedance 1.5 Pro makes a video and its sound together in one pass, so voices, effects and ambience line up with the picture and lips match the speech. You give it a written description, optionally a still image or first and last frames, and get back 4 to 12 seconds up to Full HD. Choose it for short dialogue scenes in many languages. It takes no video or audio references; Seedance 2.0 does.
You pay for what each request uses. No subscription, no minimum.
One second of video, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Second of video | 7,67 DA |
per second of video returned
One company runs this model. OpenDunes sends every request to it.
You pay the price of the provider that served your request. Prices read 15:20 · speed over the last 30 minutes · uptime over 3 days.
Send the job, then ask for it until it is ready.
import os, time, requests
BASE = "https://opendunes.com/v1"
KEY = os.environ["OPENDUNES_API_KEY"]
H = {"Authorization": f"Bearer {KEY}"}
job = requests.post(f"{BASE}/videos", headers=H, json={
"model": "bytedance/seedance-1-5-pro",
"prompt": "Sunrise over the dunes of Taghit, slow pan",
"duration": 8, "resolution": "1080p",
"generate_audio": False,
}).json()
while job["status"] not in ("completed", "failed"):
time.sleep(10)
job = requests.get(job["polling_url"], headers=H).json()
print(f"{BASE}/videos/{job['id']}/content")Runs this request once on your balance.
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
frequency_penaltyAbout 7,67 DA per second of video.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
Seedance 1.5 Pro makes a video and its sound together in one pass, so voices, effects and ambience line up with the picture and lips match the speech. You give it a written description, optionally a still image or first and last frames, and get back 4 to 12 seconds up to Full HD. Choose it for short dialogue scenes in many languages. It takes no video or audio references; Seedance 2.0 does.
Deposit dinars with your Edahabia or CIB card. Every model, Seedance 1.5 Pro included, is paid from that balance. No foreign card, no conversion.
Bytedance names no languages for Seedance 1.5 Pro. Arabic, French and Darja: not stated.
4 to 12 seconds. With sound, priced apart.
From a first and a last frame. Vertical 9:16: yes.
Bytedance. Released 23 March 2026.
Seedance 2.0 turns a written description, still images, video clips or audio references into a video with matching sound, 4 to 15 seconds long. Give it pictures of a character and it keeps that person recognisable from shot to shot, and you can fix the first and last frame of a clip. It is the only model in the Seedance line here that goes up to 4K.
Seedance 2.0 Fast takes the same text, image, video and audio inputs as Seedance 2.0 and gives back a 4 to 15 second clip with sound, in low resolution or HD. It is built for speed, so it suits storyboards, ad drafts and testing many ideas before you commit to one. Once a description works, rerun it on Seedance 2.0 when you need Full HD or 4K delivery. Mini sits below Fast in the same line and shares its HD ceiling.
Seedance 2.0 Mini takes a written description plus image, video and audio references and gives back a 4 to 15 second clip with sound, in low resolution or HD; you can also set the first and last frame. Use it for high-volume drafting where each clip is judged quickly. For sharper pictures move to Seedance 2.0 (up to 4K); Seedance 2.0 Fast shares the same size limits but is the version tuned for speed.
Seedance 2.5 is the pick when one clip must run long: it makes up to 30 seconds in a single pass and can be extended twice more. It takes a written description plus image, video and audio references, lets you set the opening frame or both end frames, and edits existing footage, including green-screen replacement. Output stops at HD.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Makes sound
The video comes with sound.
Animates your photo
Turns your picture into the first frame.
First + last frame
You set where the video starts and ends.
Vertical 9:16
Same result twice
The same seed gives the same result.
Up to 12 s
Make a clip where two characters talk to each other
Make a product ad with sound effects that match the action
Animate a photo into a scene with a camera orbit
Images