Providers and ModelsByteDance

Seedance 1.5 Pro

Seedance 1.5 Pro
ByteDance · Video Generation
POST /v1/videos/generations

Joint audio and video generation with millisecond lip sync, dialogue in six languages, cinematic camera moves, and up to 1080p output.

At a glance

FieldValue
Model idseedance-1-5-pro
Model release date2025-12-19
Input modalitiesText, Image
Output modalitiesVideo
Context window-
Weight precision-
RegionMalaysia
Featurestext_to_video, image_to_video, audio_sync, lip_sync, camera_control, seed_control
Native inferenceNo
NewNo
Supported endpointsPOST /v1/videos/generations
Alternate model idsbytedance/seedance-1.5-pro, seedance-1.5-pro, seedance-1-5-pro-251215

Pricing

ChargeSpecRate
With Audio 480Pper second$0.048
With Audio 720Pper second$0.104
With Audio 1080Pper second$0.233
No Audio 480Pper second$0.024
No Audio 720Pper second$0.052
No Audio 1080Pper second$0.117

Example request

$curl https://api.empiriolabs.ai/v1/videos/generations \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -H 'Content-Type: application/json' \
>  -d '{"model": "seedance-1-5-pro", "prompt": "sunrise over the ocean", "duration": 6}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyes-Scene description. Put spoken dialogue in double quotes for lip-synced speech; native audio (dialogue, effects, music) is generated with the video.
modeenumno"auto"auto: detect from the inputs you attach. t2v: text-to-video. i2v_first: animate a first frame. i2v_both: animate between a first and last frame. · Allowed: auto, t2v, i2v_first, i2v_both
resolutionenumno"720p"Output resolution. Audio and silent generations bill at different per-second rates for each resolution. · Allowed: 480p, 720p, 1080p
aspect_ratioenumno"adaptive"adaptive lets the model choose. First-frame jobs follow the input image’s aspect ratio. · Allowed: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9
custom_durationbooleannotrueIf false, the model picks the clip length itself. If true, use the duration field.
durationnumberno5Clip length in seconds. Only used when custom_duration is true. · Range: 4 – 12
generate_audiobooleannotrueGenerate native synchronized audio (dialogue, effects, music) with the video. Silent output bills at a lower rate.
camera_fixedbooleannofalseAsk the model to keep the camera position fixed.
seednumberno-Integer seed for reproducible-style output. Same seed gives similar, not identical, results. · Range: -1 – 2147483647
draftbooleannofalseRender a cheaper 480p draft first. Re-render the pick at full quality by passing its job id as draft_task_id.
return_last_framebooleannofalseAlso return the final frame as a PNG, ready to use as the first frame of the next clip.
imagestringno-First frame image URL.
image_endstringno-End-frame image URL for i2v_both.
draft_task_idstringno-Job id of a previous draft generation to re-render at full quality. Reuses the draft’s prompt, images, audio setting, and seed.
negative_promptstringno""What to avoid.

Notes

ByteDance’s first joint audio-video model: sound (dialogue, effects, music) is generated together with the picture in one pass.

Modes

  • Text to video, first frame, or first and last frame. No video, audio, or multi-image reference input.
  • Put spoken lines in double quotes in the prompt for lip-synced dialogue. Speech covers English, Mandarin and several Chinese dialects, Japanese, Korean, Spanish, and Indonesian.

Output

  • 480p, 720p, and 1080p at 24fps, 4 to 12 seconds (or let the model pick the length), MP4 with mono audio.
  • generate_audio is on by default; silent output bills at the lower no-audio rate.

Draft mode

  • draft renders a cheap 480p preview at a reduced rate. Re-render a pick at full quality by passing its job id as draft_task_id.

Input limits

  • Images: jpeg, png, webp, bmp, tiff, gif, heic, or heif, 300 to 6000 px per side, aspect ratio between 0.4 and 2.5, under 30 MB each.

Billing

  • Billed per second of generated video at the rate for the output resolution, with separate audio and silent rates. The model meters generated frames, so billed seconds track the rendered output; draft renders bill fewer seconds.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/seedance-1-5-pro.