> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server. # Seedance 1.5 Pro > Joint audio and video generation with millisecond lip sync, dialogue in six languages, cinematic camera moves, and up to 1080p output. ![Seedance 1.5 Pro](https://media.empiriolabs.ai/model-logos/seedance-1-5-pro.png) [ByteDance](/providers/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 | Field | Value | | ------------------- | ----------------------------------------------------------------------------------------- | | Model id | `seedance-1-5-pro` | | Model release date | 2025-12-19 | | Input modalities | Text, Image | | Output modalities | Video | | Context window | - | | Weight precision | - | | Region | Malaysia | | Features | text\_to\_video, image\_to\_video, audio\_sync, lip\_sync, camera\_control, seed\_control | | Native inference | No | | New | No | | Supported endpoints | `POST /v1/videos/generations` | | Alternate model ids | `bytedance/seedance-1.5-pro`, `seedance-1.5-pro`, `seedance-1-5-pro-251215` | ## Pricing | Charge | Spec | Rate | | ---------------- | ---------- | ------- | | With Audio 480P | per second | \$0.048 | | With Audio 720P | per second | \$0.104 | | With Audio 1080P | per second | \$0.233 | | No Audio 480P | per second | \$0.024 | | No Audio 720P | per second | \$0.052 | | No Audio 1080P | per second | \$0.117 | ## Example request ```bash 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 | Parameter | Type | Required | Default | Description | | ------------------- | ------- | -------- | ------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `prompt` | string | yes | - | Scene description. Put spoken dialogue in double quotes for lip-synced speech; native audio (dialogue, effects, music) is generated with the video. | | `mode` | enum | no | `"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` | | `resolution` | enum | no | `"720p"` | Output resolution. Audio and silent generations bill at different per-second rates for each resolution. · Allowed: `480p`, `720p`, `1080p` | | `aspect_ratio` | enum | no | `"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_duration` | boolean | no | true | If false, the model picks the clip length itself. If true, use the duration field. | | `duration` | number | no | `5` | Clip length in seconds. Only used when custom\_duration is true. · Range: 4 – 12 | | `generate_audio` | boolean | no | true | Generate native synchronized audio (dialogue, effects, music) with the video. Silent output bills at a lower rate. | | `camera_fixed` | boolean | no | false | Ask the model to keep the camera position fixed. | | `seed` | number | no | - | Integer seed for reproducible-style output. Same seed gives similar, not identical, results. · Range: -1 – 2147483647 | | `draft` | boolean | no | false | Render a cheaper 480p draft first. Re-render the pick at full quality by passing its job id as draft\_task\_id. | | `return_last_frame` | boolean | no | false | Also return the final frame as a PNG, ready to use as the first frame of the next clip. | | `image` | string | no | - | First frame image URL. | | `image_end` | string | no | - | End-frame image URL for i2v\_both. | | `draft_task_id` | string | no | - | Job id of a previous draft generation to re-render at full quality. Reuses the draft's prompt, images, audio setting, and seed. | | `negative_prompt` | string | no | `""` | 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`.