Call Seedance 2.5 and Seedance 2.5 Flash from Python with one function per endpoint: text-to-video, image-to-video, reference-to-video, video editing, video extension, motion control, talking avatar. Built on the official wavespeed SDK and the WaveSpeedAI hosted API — no GPU, pay per generation.
- Seedance 2.5 API guide, live pricing and playground: wavespeed.ai/seedance-2-5-api
- No code: generate in the browser with the AI Video Generator on WaveSpeedAI
pip install git+https://github.com/WaveSpeedAI/seedance-2.5-api.git
export WAVESPEED_API_KEY="your-api-key" # https://wavespeed.ai/accesskeyimport seedance_api
urls = seedance_api.text_to_video(
prompt="A slow cinematic dolly shot through a rain-soaked neon night market, reflections on the pavement",
)
print(urls[0])Every function waits for the generation to finish and returns a list of output URLs. Optional arguments you leave out are not sent, so the API defaults apply. Inputs such as images, videos and audio are passed as URLs; use seedance_api.upload("local-file") to get a URL for a local file.
Each model page has a playground, live pricing and copy-paste API snippets. Prices are per generation and depend on the settings you choose; check a request before running it with wavespeed price <model> from the CLI.
bytedance/seedance-2.5/text-to-video — Seedance 2.5 (Text-to-Video) generates Hollywood-grade cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability. Built on ByteDance Seed's unified multimodal architecture, it leads on instruction adherence, motion quality, and visual aesthetics.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the scene, action, camera movement, and mood for the video. | ||
reference_images |
List[str] | up to 30 items | Reference image URLs to guide visual style, characters, or scene composition. | ||
reference_videos |
List[str] | up to 10 items | Reference video URLs (total length must not exceed 30 seconds). | ||
reference_audios |
List[str] | up to 10 items | Reference audio URLs (total length must not exceed 30 seconds). | ||
aspect_ratio |
str | "16:9" |
16:9, 9:16, 4:3, 3:4, 1:1, 21:9 |
The aspect ratio of the generated video. | |
resolution |
str | "720p" |
480p, 720p, 1080p, 4k |
The output video resolution. | |
duration |
int | 5 |
4–30 | The duration of the generated video in seconds (4-30s). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. | ||
output_format |
str | "mp4" |
mp4, mov |
The container of the output video. mov is a QuickTime file with 4:4:4 video (H.264 up to 1080p, HEVC 10-bit at 4k) and uncompressed audio, intended for post-production; some browsers and players cannot play it. |
bytedance/seedance-2.5/text-to-video-turbo — Seedance 2.5 (Text-to-Video Turbo) generates cinematic videos from text prompts at 720p and 1080p with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability — optimized for turbo output. Built on ByteDance Seed's unified multimodal architecture.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the scene, action, camera movement, and mood for the video. | ||
reference_images |
List[str] | up to 30 items | Reference image URLs to guide visual style, characters, or scene composition. | ||
reference_videos |
List[str] | up to 10 items | Reference video URLs (total length must not exceed 30 seconds). | ||
reference_audios |
List[str] | up to 10 items | Reference audio URLs (total length must not exceed 30 seconds). | ||
aspect_ratio |
str | "16:9" |
16:9, 9:16, 4:3, 3:4, 1:1, 21:9 |
The aspect ratio of the generated video. | |
resolution |
str | "720p" |
720p, 1080p |
The output video resolution. | |
duration |
int | 5 |
4–30 | The duration of the generated video in seconds (4-30s). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. |
bytedance/seedance-2.5/image-to-video — Seedance 2.5 (Image-to-Video) generates Hollywood-grade cinematic videos from reference images and text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability. Built on ByteDance Seed's unified multimodal architecture, it preserves the input image's subject and composition while adding expressive, physically accurate motion.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the scene, action, camera movement, and mood for the video. | ||
image |
str | yes | Start image URL to guide the video generation. | ||
last_image |
str | Last frame image URL for video continuation. | |||
resolution |
str | "720p" |
480p, 720p, 1080p, 4k |
The output video resolution. | |
duration |
int | 5 |
4–30 | The duration of the generated video in seconds (4-30s). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. | ||
output_format |
str | "mp4" |
mp4, mov |
The container of the output video. mov is a QuickTime file with 4:4:4 video (H.264 up to 1080p, HEVC 10-bit at 4k) and uncompressed audio, intended for post-production; some browsers and players cannot play it. |
bytedance/seedance-2.5/image-to-video-turbo — Seedance 2.5 (Image-to-Video Turbo) generates cinematic 720p/1080p videos from reference images and text prompts —a faster, more affordable high-resolution tier with native audio-visual synchronization, director-level control, and exceptional motion stability. Built on ByteDance Seed's unified multimodal architecture.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the scene, action, camera movement, and mood for the video. | ||
image |
str | yes | Start image URL to guide the video generation. | ||
last_image |
str | Last frame image URL for video continuation. | |||
resolution |
str | "720p" |
720p, 1080p |
The output video resolution. | |
duration |
int | 5 |
4–30 | The duration of the generated video in seconds (4-30s). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. |
bytedance/seedance-2.5/reference-to-video — Seedance 2.5 Reference to Video creates cinematic videos with native audio from your own reference images, videos, and audio, keeping characters, products, motion, and sound consistent while a prompt directs the new shot.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the scene, action, camera movement, and mood for the video. Refer to reference media as @Image 1, @Video 1, @Audio 1 (in upload order) and say what each is for. | ||
reference_images |
List[str] | up to 30 items | Reference image URLs to keep characters, products, or scenes consistent and to guide style and composition. Provide at least one reference image, video, or audio; with none, the request runs as text-to-video. | ||
reference_videos |
List[str] | up to 10 items | Reference video URLs for motion, camera work, or a character to follow (total length must not exceed 30 seconds). | ||
reference_audios |
List[str] | up to 10 items | Reference audio URLs for voice, music, or sound style (total length must not exceed 30 seconds). | ||
aspect_ratio |
str | "16:9" |
16:9, 9:16, 4:3, 3:4, 1:1, 21:9 |
The aspect ratio of the generated video. | |
resolution |
str | "720p" |
480p, 720p, 1080p, 4k |
The output video resolution. | |
duration |
int | 5 |
4–30 | The duration of the generated video in seconds (4-30s). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. | ||
output_format |
str | "mp4" |
mp4, mov |
The container of the output video. mov is a QuickTime file with 4:4:4 video (H.264 up to 1080p, HEVC 10-bit at 4k) and uncompressed audio, intended for post-production; some browsers and players cannot play it. |
bytedance/seedance-2.5/reference-to-video-turbo — Seedance 2.5 Turbo Reference to Video creates cinematic videos with native audio from your own reference images, videos, and audio, keeping characters, products, motion, and sound consistent while a prompt directs the new shot.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the scene, action, camera movement, and mood for the video. Refer to reference media as @Image 1, @Video 1, @Audio 1 (in upload order) and say what each is for. | ||
reference_images |
List[str] | up to 30 items | Reference image URLs to keep characters, products, or scenes consistent and to guide style and composition. Provide at least one reference image, video, or audio; with none, the request runs as text-to-video. | ||
reference_videos |
List[str] | up to 10 items | Reference video URLs for motion, camera work, or a character to follow (total length must not exceed 30 seconds). | ||
reference_audios |
List[str] | up to 10 items | Reference audio URLs for voice, music, or sound style (total length must not exceed 30 seconds). | ||
aspect_ratio |
str | "16:9" |
16:9, 9:16, 4:3, 3:4, 1:1, 21:9 |
The aspect ratio of the generated video. | |
resolution |
str | "720p" |
720p, 1080p |
The output video resolution. | |
duration |
int | 5 |
4–30 | The duration of the generated video in seconds (4-30s). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. |
bytedance/seedance-2.5/video-edit — Seedance 2.5 (Video-Edit) edits an input video from a natural-language prompt. The reference video drives subject identity, composition, and motion while the model rewrites lighting, style, weather, environment, or specific elements as instructed. Built on ByteDance Seed's unified multimodal architecture for cinematic, motion-stable output.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the edit you want applied to the input video. | ||
video |
str | yes | URL of the input video to edit. Videos longer than 30s are trimmed to 30s; videos shorter than 4s are padded to 4s. | ||
reference_images |
List[str] | up to 30 items | Optional reference image URLs to guide the edit (subject identity, style, etc.). | ||
reference_audios |
List[str] | up to 10 items | Optional reference audio URLs to guide audio generation. | ||
resolution |
str | "720p" |
480p, 720p, 1080p, 4k |
Output video resolution. | |
generate_audio |
bool | true |
Whether to generate native audio for the edited output. Defaults to true. When set to false, the input video's audio track is preserved on the output instead. | ||
output_format |
str | "mp4" |
mp4, mov |
The container of the output video. mov is a QuickTime file with 4:4:4 video (H.264 up to 1080p, HEVC 10-bit at 4k) and uncompressed audio, intended for post-production; some browsers and players cannot play it. |
bytedance/seedance-2.5/video-edit-turbo — Seedance 2.5 (Video-Edit Turbo) is the turbo tier for editing an input video from a natural-language prompt — faster, more affordable high-resolution output while preserving subject identity, composition, and motion.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the edit you want applied to the input video. | ||
video |
str | yes | URL of the input video to edit. Videos longer than 30s are trimmed to 30s; videos shorter than 4s are padded to 4s. | ||
reference_images |
List[str] | up to 30 items | Optional reference image URLs to guide the edit (subject identity, style, etc.). | ||
reference_audios |
List[str] | up to 10 items | Optional reference audio URLs to guide audio generation. | ||
resolution |
str | "720p" |
720p, 1080p |
Turbo output resolution. | |
generate_audio |
bool | true |
Whether to generate native audio for the edited output. Defaults to true. When set to false, the input video's audio track is preserved on the output instead. |
bytedance/seedance-2.5/video-extend — Seedance 2.5 (Video-Extend) extends an input video with a new cinematic continuation generated from its last frame and a natural-language prompt.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the cinematic continuation - action, camera movement, lighting, mood. | ||
video |
str | yes | URL of the input video to extend. The native extension uses the last 30 seconds as context; generation continues seamlessly from the ending. | ||
resolution |
str | "720p" |
480p, 720p, 1080p, 4k |
Output resolution of the new segment. | |
duration |
int | 5 |
4–30 | Length in seconds of the new segment to append (4-30). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. |
bytedance/seedance-2.5/motion-control — Transfer the motion of a reference video onto a character with Seedance 2.5. Your character, from a picture or a short description, performs the same movements, gestures and camera motion as the video, in 480p, 720p or 1080p for up to 30 seconds.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
video |
str | yes | URL of the motion reference video, 4 to 30 seconds. Only the first 30 seconds of a longer video are used, and a shorter video is billed as 4 seconds. The result follows its duration, camera and background. | ||
reference_images |
List[str] | up to 30 items | Optional reference image URLs. The first image is the character who performs the motion. Add pictures of an outfit, props or a location to use them in the shot (30 images at most). Without any image, describe the character in the prompt. | ||
prompt |
str | Optional extra direction for the result. Required when no reference image is given: describe the character who replaces the person in the video. | |||
resolution |
str | "720p" |
480p, 720p, 1080p |
Output video resolution. | |
generate_audio |
bool | true |
Whether to generate native audio for the output. Defaults to true. When set to false, the reference video's audio track is preserved on the output instead. |
bytedance/seedance-2.5/talking-avatar — Animate a portrait image from an audio recording with Seedance 2.5. Generate talking-avatar videos in 480p or 720p, processing up to the first 120 seconds of audio.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
image |
str | yes | URL of the portrait image to animate. | ||
audio |
str | yes | URL of a nonempty audio recording. Only the first 120 seconds are processed; longer recordings are accepted and trimmed automatically. | ||
prompt |
str | Optional guidance for the avatar's expression and movement. Leave empty to use natural speaking behavior. | |||
resolution |
str | "720p" |
480p, 720p |
Output video resolution. |
bytedance/seedance-2.5-flash/text-to-video — Seedance 2.5 Flash Text-to-Video creates videos from text prompts and optional image, video, and audio references, with 480p or 720p output and optional generated audio.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the scene, action, camera movement, and mood for the video. | ||
reference_images |
List[str] | up to 10 items | Reference image URLs to guide visual style, characters, or scene composition. | ||
reference_videos |
List[str] | up to 5 items | Reference video URLs (total length must not exceed 30 seconds). | ||
reference_audios |
List[str] | up to 5 items | Reference audio URLs (total length must not exceed 30 seconds). | ||
aspect_ratio |
str | "16:9" |
16:9, 9:16, 4:3, 3:4, 1:1, 21:9 |
The aspect ratio of the generated video. | |
resolution |
str | "720p" |
480p, 720p, 1080p, 4k |
The output video resolution. 1080p and 4k are generated at 720p and upscaled. | |
duration |
int | 5 |
4–30 | The duration of the generated video in seconds (4-30s). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. | ||
output_format |
str | "mp4" |
mp4, mov |
The container of the output video. mov is a QuickTime file with H.264 4:4:4 video and uncompressed audio, intended for post-production; some browsers and players cannot play it. mov is not available at 1080p or 4k. |
bytedance/seedance-2.5-flash/text-to-video-turbo — Seedance 2.5 Flash Text-to-Video creates videos from text prompts and optional image, video, and audio references, with 480p or 720p output and optional generated audio.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the scene, action, camera movement, and mood for the video. | ||
reference_images |
List[str] | up to 10 items | Reference image URLs to guide visual style, characters, or scene composition. | ||
reference_videos |
List[str] | up to 5 items | Reference video URLs (total length must not exceed 30 seconds). | ||
reference_audios |
List[str] | up to 5 items | Reference audio URLs (total length must not exceed 30 seconds). | ||
aspect_ratio |
str | "16:9" |
16:9, 9:16, 4:3, 3:4, 1:1, 21:9 |
The aspect ratio of the generated video. | |
resolution |
str | "720p" |
720p, 1080p |
The output video resolution. The video is generated at 480p and upscaled. | |
duration |
int | 5 |
4–30 | The duration of the generated video in seconds (4-30s). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. |
bytedance/seedance-2.5-flash/image-to-video — Seedance 2.5 Flash Image-to-Video animates a start image using text instructions, with an optional last frame, 480p or 720p output, and optional generated audio.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the scene, action, camera movement, and mood for the video. | ||
image |
str | yes | Start image URL to guide the video generation. | ||
last_image |
str | Last frame image URL for video continuation. | |||
resolution |
str | "720p" |
480p, 720p, 1080p, 4k |
The output video resolution. 1080p and 4k are generated at 720p and upscaled. | |
duration |
int | 5 |
4–30 | The duration of the generated video in seconds (4-30s). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. | ||
output_format |
str | "mp4" |
mp4, mov |
The container of the output video. mov is a QuickTime file with H.264 4:4:4 video and uncompressed audio, intended for post-production; some browsers and players cannot play it. mov is not available at 1080p or 4k. |
bytedance/seedance-2.5-flash/image-to-video-turbo — Seedance 2.5 Flash Image-to-Video animates a start image using text instructions, with an optional last frame, 480p or 720p output, and optional generated audio.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the scene, action, camera movement, and mood for the video. | ||
image |
str | yes | Start image URL to guide the video generation. | ||
last_image |
str | Last frame image URL for video continuation. | |||
resolution |
str | "720p" |
720p, 1080p |
The output video resolution. The video is generated at 480p and upscaled. | |
duration |
int | 5 |
4–30 | The duration of the generated video in seconds (4-30s). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. |
bytedance/seedance-2.5-flash/reference-to-video — Seedance 2.5 Flash Reference-to-Video creates videos guided by text and optional image, video, and audio references, with 480p or 720p output and optional generated audio.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the scene, action, camera movement, and mood for the video. Refer to reference media as @Image 1, @Video 1, @Audio 1 (in upload order) and say what each is for. | ||
reference_images |
List[str] | up to 10 items | Reference image URLs to keep characters, products, or scenes consistent and to guide style and composition. Provide at least one reference image, video, or audio; with none, the request runs as text-to-video. | ||
reference_videos |
List[str] | up to 5 items | Reference video URLs for motion, camera work, or a character to follow (total length must not exceed 30 seconds). | ||
reference_audios |
List[str] | up to 5 items | Reference audio URLs for voice, music, or sound style (total length must not exceed 30 seconds). | ||
aspect_ratio |
str | "16:9" |
16:9, 9:16, 4:3, 3:4, 1:1, 21:9 |
The aspect ratio of the generated video. | |
resolution |
str | "720p" |
480p, 720p, 1080p, 4k |
The output video resolution. 1080p and 4k are generated at 720p and upscaled. | |
duration |
int | 5 |
4–30 | The duration of the generated video in seconds (4-30s). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. | ||
output_format |
str | "mp4" |
mp4, mov |
The container of the output video. mov is a QuickTime file with H.264 4:4:4 video and uncompressed audio, intended for post-production; some browsers and players cannot play it. mov is not available at 1080p or 4k. |
bytedance/seedance-2.5-flash/reference-to-video-turbo — Seedance 2.5 Flash Reference-to-Video creates videos guided by text and optional image, video, and audio references, with 480p or 720p output and optional generated audio.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the scene, action, camera movement, and mood for the video. Refer to reference media as @Image 1, @Video 1, @Audio 1 (in upload order) and say what each is for. | ||
reference_images |
List[str] | up to 10 items | Reference image URLs to keep characters, products, or scenes consistent and to guide style and composition. Provide at least one reference image, video, or audio; with none, the request runs as text-to-video. | ||
reference_videos |
List[str] | up to 5 items | Reference video URLs for motion, camera work, or a character to follow (total length must not exceed 30 seconds). | ||
reference_audios |
List[str] | up to 5 items | Reference audio URLs for voice, music, or sound style (total length must not exceed 30 seconds). | ||
aspect_ratio |
str | "16:9" |
16:9, 9:16, 4:3, 3:4, 1:1, 21:9 |
The aspect ratio of the generated video. | |
resolution |
str | "720p" |
720p, 1080p |
The output video resolution. The video is generated at 480p and upscaled. | |
duration |
int | 5 |
4–30 | The duration of the generated video in seconds (4-30s). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. |
bytedance/seedance-2.5-flash/video-edit — Seedance 2.5 Flash Video Edit edits a source video using text instructions and optional image and audio references, with 480p or 720p output.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the edit you want applied to the input video. | ||
video |
str | yes | URL of the input video to edit. Videos longer than 30s are trimmed to 30s; videos shorter than 4s are padded to 4s. | ||
reference_images |
List[str] | up to 10 items | Optional reference image URLs to guide the edit (subject identity, style, etc.). | ||
reference_audios |
List[str] | up to 5 items | Optional reference audio URLs to guide audio generation. | ||
resolution |
str | "720p" |
480p, 720p, 1080p, 4k |
Output video resolution. 1080p and 4k are generated at 720p and upscaled. | |
generate_audio |
bool | true |
Whether to generate native audio for the edited output. Defaults to true. When set to false, the input video's audio track is preserved on the output instead. | ||
output_format |
str | "mp4" |
mp4, mov |
The container of the output video. mov is a QuickTime file with H.264 4:4:4 video and uncompressed audio, intended for post-production; some browsers and players cannot play it. mov is not available at 1080p or 4k. |
bytedance/seedance-2.5-flash/video-edit-turbo — Seedance 2.5 Flash Video Edit edits a source video using text instructions and optional image and audio references, with 480p or 720p output.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the edit you want applied to the input video. | ||
video |
str | yes | URL of the input video to edit. Videos longer than 30s are trimmed to 30s; videos shorter than 4s are padded to 4s. | ||
reference_images |
List[str] | up to 10 items | Optional reference image URLs to guide the edit (subject identity, style, etc.). | ||
reference_audios |
List[str] | up to 5 items | Optional reference audio URLs to guide audio generation. | ||
resolution |
str | "720p" |
720p, 1080p |
The output video resolution. The video is generated at 480p and upscaled. | |
generate_audio |
bool | true |
Whether to generate native audio for the edited output. Defaults to true. When set to false, the input video's audio track is preserved on the output instead. |
bytedance/seedance-2.5-flash/video-extend — Seedance 2.5 Flash (Video-Extend) extends an input video with a new cinematic continuation generated from its last frame and a natural-language prompt.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
prompt |
str | yes | Describe the cinematic continuation - action, camera movement, lighting, mood. | ||
video |
str | yes | URL of the input video to extend. The native extension uses the last 30 seconds as context; generation continues seamlessly from the ending. | ||
resolution |
str | "720p" |
480p, 720p, 1080p, 4k |
Output resolution of the new segment. 1080p and 4k are generated at 720p and upscaled. | |
duration |
int | 5 |
4–30 | Length in seconds of the new segment to append (4-30). | |
generate_audio |
bool | true |
Whether to generate native audio synchronized with the output video. Defaults to true. |
bytedance/seedance-2.5-flash/motion-control — Transfer the motion of a reference video onto a character with Seedance 2.5 Flash. Your character, from a picture or a short description, performs the same movements, gestures and camera motion as the video, in 480p, 720p or 1080p for up to 30 seconds.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
video |
str | yes | URL of the motion reference video, 4 to 30 seconds. Only the first 30 seconds of a longer video are used, and a shorter video is billed as 4 seconds. The result follows its duration, camera and background. | ||
reference_images |
List[str] | up to 10 items | Optional reference image URLs. The first image is the character who performs the motion. Add pictures of an outfit, props or a location to use them in the shot (10 images at most). Without any image, describe the character in the prompt. | ||
prompt |
str | Optional extra direction for the result. Required when no reference image is given: describe the character who replaces the person in the video. | |||
resolution |
str | "720p" |
480p, 720p, 1080p |
Output video resolution. 1080p is generated at 720p and upscaled. | |
generate_audio |
bool | true |
Whether to generate native audio for the output. Defaults to true. When set to false, the reference video's audio track is preserved on the output instead. |
bytedance/seedance-2.5-flash/talking-avatar — Animate a portrait image from an audio recording with Seedance 2.5 Flash. Generate talking-avatar videos in 480p or 720p, processing up to the first 120 seconds of audio.
| Parameter | Type | Required | Default | Allowed | Description |
|---|---|---|---|---|---|
image |
str | yes | URL of the portrait image to animate. | ||
audio |
str | yes | URL of a nonempty audio recording. Only the first 120 seconds are processed; longer recordings are accepted and trimmed automatically. | ||
prompt |
str | Optional guidance for the avatar's expression and movement. Leave empty to use natural speaking behavior. | |||
resolution |
str | "720p" |
480p, 720p |
Output video resolution. |
The wrapper is a thin layer over the REST API: submit, then poll for the result.
curl -s -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.5/text-to-video" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" -H "Content-Type: application/json" \
-d '{"prompt": "A slow cinematic dolly shot through a rain-soaked neon night market, reflections on the pavement"}'
# -> {"data": {"id": "<prediction_id>"}}
curl -s "https://api.wavespeed.ai/api/v3/predictions/<prediction_id>/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# -> status: completed, outputs: ["<url>"]npm i -g @wavespeed/cli && wavespeed login
wavespeed run bytedance/seedance-2.5/text-to-video -p "your prompt"- awesome-seedance-api — prompt library and variant guide
- More model wrappers: Wan 3.0 · Kling 4.0 · Veo 3.1 · MiniMax H3 · HappyHorse 1.1 · FLUX 3 · Seedream 5.5 · GPT Image 2.6 · Nano Banana 2.1
- SDKs and tools: Python · JavaScript · CLI · MCP server · ComfyUI nodes
- Full model catalog
- Seedance 2.5 is a model by ByteDance. This repository is maintained by WaveSpeedAI and wraps the WaveSpeedAI hosted API for it.
- Function signatures and the tables above are generated from the live model schemas (last generated 2026-11-22). The model pages are the source of truth if an endpoint changes.
- Issues and pull requests are welcome. License: MIT.