# Seedance 2.5 Flash > Generate multimodal AI video with synchronized native audio from text, images, video or audio references at 480p or 720p. ## Overview - **Endpoint**: `https://api.segmind.com/v1/seedance-2.5-flash` - **Model ID**: `seedance-2.5-flash` - **Category**: Image-to-Video Generation - **Type**: Synchronous (Direct response) - **Average Latency**: ~100.3s (30-day average) - **Average Cost**: $1.822 per run (observed across past runs, not a price — see Pricing) - **Provider**: BYTEDANCE ## Pricing | Input Type | Resolution | Rate | | --- | --- | --- | | Text or image input | 480p | $7.36841 per million tokens | | Text or image input | 720p | $7.36841 per million tokens | | Video input | 480p | $4.526309 per million tokens | | Video input | 720p | $4.526309 per million tokens | Billed per million video tokens: output width x height x frame rate x duration / 1024. With a reference video, every reference video is billed at the video-input rate on top of the output. ## Pricing Notes ### Pricing Seedance 2.5 Flash is billed by output resolution, aspect ratio and length, at about a third less than Seedance 2.5. #### Per second of output | Resolution | Input | 16:9 | 9:16 | 1:1 | 4:3 | 3:4 | 21:9 | |---|---|---|---|---|---|---|---| | 480p | Text / image | $0.0715 | $0.0715 | $0.0684 | $0.0703 | $0.0703 | $0.0715 | | 720p | Text / image | $0.1605 | $0.1605 | $0.1605 | $0.1615 | $0.1615 | $0.1613 | | 480p | With reference video | $0.0439 | $0.0439 | $0.0420 | $0.0432 | $0.0432 | $0.0439 | | 720p | With reference video | $0.0986 | $0.0986 | $0.0986 | $0.0992 | $0.0992 | $0.0991 | With a reference video, the request is priced at the reference-video rate, and the reference video's own length is billed at that rate on top of the output. #### Examples (16:9) | Input | Resolution | Duration | Price | |---|---|---|---| | Text / image | 480p | 5s | $0.36 | | Text / image | 720p | 5s | $0.80 | | Text / image | 720p | 10s | $1.61 | | Text / image | 720p | 30s | $4.82 | #### How the charge works 1. **On request**: a temporary hold is placed on your credits. 2. **On completion**: you are charged for the video actually rendered; the rest of the hold is released. 3. **Failed or moderated renders** are not charged. #### Tips - Iterate at 480p, then render the final at 720p. - Need 1080p or longer reference sets? Use seedance-2.5. ## API Information This model uses a **synchronous response pattern**: 1. Make a POST request with your parameters 2. Receive the output directly in the response: the generated file itself, saved here as `output.mp4` (if the Content-Type is JSON, read it as JSON instead) 3. No polling required - response is immediate ### Input Schema The API accepts the following input parameters: - **`prompt`** (`string`, _required_): Prompt Text describing the video. Use Shot 1:, Shot 2: for multi-shot sequences. Reference uploaded assets as '@Image 1', '@Video 1', '@Audio 1' in your prompt. - **`first_frame_url`** (`File (URL)`, _optional_): First Frame Image Starting frame image URL for image-to-video. Animates outward from this reference. Note: images with real human faces are blocked by ByteDance content policy. Cannot be used together with reference_images. - **`last_frame_url`** (`File (URL)`, _optional_): Last Frame Image Ending frame; requires first_frame_url. Guides transitions between two frames. - **`reference_images`** (`array`, _optional_): Reference Images Up to 10 reference images (max 30MB each) for character/style consistency. Cite as '@Image 1', '@Image 2' in your prompt. Cannot be used together with first_frame_url. - Item type: string - **`reference_videos`** (`array`, _optional_): Reference Videos Up to 5 reference videos (2-30 seconds each, 30 seconds combined, mp4/mov, max 200MB each) for motion/style transfer. Cite as '@Video 1' in your prompt. Requests with reference videos are billed at the video-input token rate. - Item type: string - **`reference_audios`** (`array`, _optional_): Reference Audios Up to 5 reference audio files (MP3, 2-30 seconds each, 30 seconds combined, max 15MB each). Cite as '@Audio 1' in your prompt. Audio-only reference is supported. - Item type: string - **`duration`** (`integer`, _optional_): Duration Video length in seconds (4-30), or -1 to let the model choose. Video-editing prompts require -1 (output follows the input video, which must be 4-30s). Cost scales with output duration (token-based). - Default: `5` - Options: "-1" (Auto (use for video edits)), "4" (4s), "5" (5s), "6" (6s), "7" (7s), "8" (8s), "9" (9s), "10" (10s), "11" (11s), "12" (12s), "13" (13s), "14" (14s), "15" (15s), "16" (16s), "17" (17s), "18" (18s), "19" (19s), "20" (20s), "21" (21s), "22" (22s), "23" (23s), "24" (24s), "25" (25s), "26" (26s), "27" (27s), "28" (28s), "29" (29s), "30" (30s) - **`resolution`** (`string`, _optional_): Resolution Output resolution: 480p or 720p (24fps). Use 480p for fast iteration, 720p for final renders. Higher resolution costs more. Use seedance-2.5 for 1080p. - Default: `"720p"` - Options: "480p" (480p), "720p" (720p) - **`aspect_ratio`** (`string`, _optional_): Aspect Ratio Output aspect ratio. Defaults to adaptive, which lets the model match the prompt or the input media. adaptive is the only value accepted when you supply first_frame_url, or when the prompt asks for a video edit or extension — the output keeps the geometry of the input in those cases. Pick a fixed ratio (16:9 landscape, 9:16 vertical, 21:9 ultrawide) for text-to-video or plain reference-to-video. - Default: `"adaptive"` - Options: "16:9" (16:9), "9:16" (9:16), "1:1" (1:1), "4:3" (4:3), "3:4" (3:4), "21:9" (21:9), "adaptive" (adaptive) - **`generate_audio`** (`boolean`, _optional_): Generate Audio Co-generate synchronized audio (dialogue, SFX, ambient, music) in the same pass. Best for scenes with speech, nature sounds, or music. - Default: `true` - **`seed`** (`integer`, _optional_): Seed Reproducibility seed. Use -1 for random output, set a fixed value to iterate on the same scene. - Default: `42` - Range: -1 to 2147483647 - **`return_last_frame`** (`boolean`, _optional_): Return Last Frame Returns the final video frame as a separate image, delivered in the response as `video.last_frame_url`. Chain shots by feeding that URL into the next generation's `first_frame_url`. Note this is an output: it is distinct from the `last_frame_url` input parameter, which is an image you supply to steer how the clip ends. - Default: `false` - **`skip_moderation`** (`boolean`, _optional_): Skip Moderation Bypass the upstream content moderation pre-filter. Useful when generating artistic content or faces that may trigger false positives. Baseline safety policies still apply. - Default: `true` - **`bitrate_mode`** (`string`, _optional_): Bitrate Mode Output video encoding bitrate. 'standard' gives smaller files and faster downloads; 'high' produces ~5-6x higher bitrate for better visual fidelity and fewer compression artifacts (larger files). Does not affect price. - Default: `"standard"` - Options: "standard" (Standard), "high" (High) - **`auto_resize`** (`boolean`, _optional_): Auto Resize Inputs Automatically resizes an input image that falls outside the provider's accepted range (300-6000px per side, aspect ratio 0.4-2.5, 30MB) so the request succeeds instead of being rejected. Aspect ratio is preserved: oversized images are downscaled, undersized ones upscaled, and out-of-band ratios padded rather than cropped. On by default - set it to false to have the provider reject out-of-range images instead. When a resize happens the response carries an X-Input-Normalized header naming the field and the before/after dimensions. - Default: `true` - **`output_codec`** (`string`, _optional_): Output Codec Codec of the delivered file. This model already returns H.264 at 480p and 720p, so 'auto' and 'h264' deliver the same file. Does not affect price. - Default: `"auto"` - Options: "auto", "h264" **Required Parameters Example**: ```json { "prompt": "Two players rally at speed across a blue table-tennis table in a school gymnasium: the white ball snaps back and forth over the net, each paddle clips it with a sharp hollow pock, and rubber-soled shoes squeak on the varnished floor as the camera tracks the volley from the side. Natural diegetic sound - the crack of each hit, the ball bouncing on the table, squeaking shoes, and the hollow echo of the hall." } ``` **Full Example**: ```json { "prompt": "Two players rally at speed across a blue table-tennis table in a school gymnasium: the white ball snaps back and forth over the net, each paddle clips it with a sharp hollow pock, and rubber-soled shoes squeak on the varnished floor as the camera tracks the volley from the side. Natural diegetic sound - the crack of each hit, the ball bouncing on the table, squeaking shoes, and the hollow echo of the hall.", "first_frame_url": "", "last_frame_url": "", "reference_images": [], "reference_videos": [], "reference_audios": [], "duration": 5, "resolution": "720p", "aspect_ratio": "16:9", "generate_audio": true, "seed": 42, "return_last_frame": false, "skip_moderation": false, "bitrate_mode": "standard" } ``` ### Output Schema The API returns a synchronous response based on the model type: **For Image/Video/Audio Models**: - Response contains binary data (image/png, video/mp4, audio/mp3) - Content-Type header indicates the media type - Save the response body directly to a file **For Text Models**: - Response is JSON with the generated text - Structure varies by model **HTTP Response Codes**: - **200 - OK**: Request successful, output in response body - **400 - Bad Request**: Invalid parameters - **401 - Unauthorized**: Invalid or missing API key - **404 - Not Found**: Model not found - **406 - Not Acceptable**: Insufficient credits - **429 - Too Many Requests**: Rate limit exceeded - **500 - Server Error**: Internal server error ## About ### Seedance 2.5 Flash — Multimodal Image & Text-to-Video #### What is Seedance 2.5 Flash? Seedance 2.5 Flash is the fast, economical tier of ByteDance Seed's Seedance 2.5, a multimodal audio-video generation model. Create 4–30 second clips at 480p or 720p from a text prompt, a first or last frame, or reference images, videos and audio — with synchronized native audio rendered in the same pass as the picture. The Flash tier trades the highest resolutions for faster turnaround and lower cost than Seedance 2.5, making it the tier for iterating and producing video at volume. #### Key Features - **Native synchronized audio** — dialogue, sound effects, ambience and music are generated together with the video and land in sync with the on-screen motion, not dubbed on afterwards. - **Multimodal referencing** — up to 10 reference images, 5 reference videos and 5 reference audio clips, cited inline as @Image, @Video and @Audio, to keep characters, style and motion consistent. - **First- and last-frame control** and multi-shot "Shot 1:" scripting for sequenced scenes. - **Video editing and extension** with timestamp-level control — adjust or lengthen a clip in place instead of regenerating it. - **Flexible output** — 4–30 second durations (or auto), 480p/720p, selectable aspect ratios, and an optional returned last frame for chaining shots. #### Best Use Cases Seedance 2.5 Flash suits social and short-form video, product and explainer clips, storyboard animatics, dialogue scenes that need lip-synced sound, and iterative pipelines where many 480p drafts get promoted to 720p finals. A reference text-to-video render returned a clean 1280×720 clip at 24fps with synchronized stereo audio. #### Prompt Tips and Output Quality Write concrete subject, action, camera move and the sound you want to hear, and keep generate_audio on for any diegetic scene. Use a fixed aspect ratio for text-to-video and adaptive when supplying a first frame or editing a clip. Fix the seed to iterate the same scene. Output is H.264 MP4 at 24fps. ## Usage Guide ### How to Use Seedance 2.5 Flash Seedance 2.5 Flash turns a text prompt — optionally with a first frame, reference images, videos or audio — into a short video with synchronized native audio. Treat it as your fast, iterate-often tier: draft cheaply at 480p, then raise the same prompt and seed to 720p for the final. #### Write the prompt Describe the subject, one clear action, the camera move, and the sound you expect ("the crack of each hit", "a low gym echo"). For a sequence, label beats as "Shot 1:", "Shot 2:". Keep generate_audio on whenever the scene has speech, effects or music — it is the model's headline capability. #### Choose inputs - **Text-to-video:** prompt only, with a fixed aspect_ratio (16:9, 9:16, 1:1, 4:3, 3:4 or 21:9). - **Image-to-video:** set first_frame_url (no real human faces) and use adaptive aspect_ratio; add last_frame_url to steer the ending. - **References:** cite up to 10 @Image, 5 @Video and 5 @Audio clips to hold a character, style or motion steady. Reference videos are billed for their full length. - **Edit or extend:** describe the change and set duration to -1 so the output follows the input clip. #### Duration and resolution Durations run 4–30 seconds. Shorter clips iterate faster; longer clips carry a story. Use 480p to explore and 720p for delivery. For 1080p use Seedance 2.5; for 4K use Seedance 2.5 4K. #### Recommended Settings Tested defaults for a clean text-to-video with sound: **duration 5, resolution 720p, aspect_ratio 16:9, generate_audio true, seed 42**. This produced a 1280×720 H.264 clip at 24fps with synchronized stereo audio in about a minute and a half. Set bitrate_mode to high when you want maximum fidelity, and return_last_frame to true to chain the next shot. #### Examples to try Every example below ran end to end at the card's settings — 5 seconds, 720p, 16:9, generate_audio on, seed 42 — so the length, framing and synchronized audio carry straight into your own runs. Click a card to load its prompt. - **Text-to-video with native sound.** Prompt: "Two players rally at speed across a blue table-tennis table in a school gymnasium: the white ball snaps back and forth over the net, each paddle clips it with a sharp hollow pock…" Each pock lands on the visible hit — audio built with the motion. Tip: name the sounds you want ("the crack of each hit") in the prompt. - **Reference-image identity consistency.** Prompt: "Keep the blue-and-red tin wind-up toy robot from @Image 1 exactly as shown — its boxy riveted body, round yellow antenna knob, two square eyes and the large silver key in its back. The robot marches stiffly across a sunlit workshop bench…" The marching robot keeps the reference's exact design. Tip: supply one clean, single-subject reference and cite it as @Image 1. - **Native audio dialogue.** Prompt: "Behind the counter of a small bakery, a baker in a flour-dusted blue apron holds up a crusty sourdough loaf, looks into the camera and says warmly, "Fresh from the oven — still warm."…" His lips move in sync with the spoken line over quiet bakery ambience. Tip: put the line in quotes and add "no subtitles". ##### Reference-guided runs The reference card takes up to 10 @Image references (and 5 @Video, 5 @Audio). Address each by number — "@Image 1 is the…", "keep @Image 2's colours" — and a clean single-subject reference holds identity best. Also built for: "Shot 1: … Shot 2: …" multi-beat scripts, "add last_frame_url to steer the ending", and "set first_frame_url to animate your own still". ## FAQ ### Does Seedance 2.5 Flash generate sound? Yes — enable generate_audio for synchronized dialogue, effects, ambience and music. ### What resolutions does it support? 480p and 720p; use Seedance 2.5 for 1080p and Seedance 2.5 4K for 4K. ### How long can a clip be? 4 to 30 seconds, or -1 to let the model choose (required for edits). ### Can I use my own images or footage? Yes — first/last frame, reference images, reference videos and reference audio are all supported. ### How is it different from Seedance 2.5? It is the same multimodal model with native audio at a faster, lower-cost tier, capped at 720p. ## Examples Requests run on the playground, the output each produced, and the API call that makes it. ### Seedance 2.5 Flash sports video generation > Two players rally at speed across a blue table-tennis table in a school gymnasium: the white ball snaps back and forth over the net, each paddle clips it with a sharp hollow pock, and rubber-soled shoes squeak on the varnished floor as the camera tracks the volley from the side. Natural diegetic sound - the crack of each hit, the ball bouncing on the table, squeaking shoes, and the hollow echo of the hall. Output: https://segmind-resources.s3.amazonaws.com/output/seedance-2.5-flash-example-output-88821495.mp4 ```bash # 1. Submit the request; the reply carries its request_id REQUEST_ID=$(curl -s -X POST "https://api.segmind.com/v2/seedance-2.5-flash" \ -H "x-api-key: YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Two players rally at speed across a blue table-tennis table in a school gymnasium: the white ball snaps back and forth over the net, each paddle clips it with a sharp hollow pock, and rubber-soled shoes squeak on the varnished floor as the camera tracks the volley from the side. Natural diegetic sound - the crack of each hit, the ball bouncing on the table, squeaking shoes, and the hollow echo of the hall.", "first_frame_url": "", "last_frame_url": "", "reference_images": [], "reference_videos": [], "reference_audios": [], "duration": 5, "resolution": "720p", "aspect_ratio": "16:9", "generate_audio": true, "seed": 42, "return_last_frame": false, "skip_moderation": false, "bitrate_mode": "standard" }' | jq -r .request_id) # 2. Check its status until it is COMPLETED curl -s "https://api.segmind.com/v2/requests/$REQUEST_ID/status" \ -H "x-api-key: YOUR_API_KEY" # 3. Fetch the result curl -s "https://api.segmind.com/v2/requests/$REQUEST_ID" \ -H "x-api-key: YOUR_API_KEY" ``` ### Seedance 2.5 Flash consistent character video > Keep the blue-and-red tin wind-up toy robot from @Image 1 exactly as shown — its boxy riveted body, round yellow antenna knob, two square eyes and the large silver key in its back. The robot marches stiffly across a sunlit workshop bench past a row of colourful wooden building blocks, arms swinging and the wind-up key turning. Static camera. Clockwork ticking and the clack of little feet on wood. Output: https://segmind-resources.s3.amazonaws.com/output/seedance-2.5-flash-example-reference-identity-a0c0089b.mp4 ```bash # 1. Submit the request; the reply carries its request_id REQUEST_ID=$(curl -s -X POST "https://api.segmind.com/v2/seedance-2.5-flash" \ -H "x-api-key: YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Keep the blue-and-red tin wind-up toy robot from @Image 1 exactly as shown — its boxy riveted body, round yellow antenna knob, two square eyes and the large silver key in its back. The robot marches stiffly across a sunlit workshop bench past a row of colourful wooden building blocks, arms swinging and the wind-up key turning. Static camera. Clockwork ticking and the clack of little feet on wood.", "first_frame_url": "", "last_frame_url": "", "reference_images": [ "https://segmind-resources.s3.amazonaws.com/input/seedance-2.5-flash-example-reference-identity-829dbcd4.jpg" ], "reference_videos": [], "reference_audios": [], "duration": 5, "resolution": "720p", "aspect_ratio": "16:9", "generate_audio": true, "seed": 42, "return_last_frame": false, "skip_moderation": false, "bitrate_mode": "standard" }' | jq -r .request_id) # 2. Check its status until it is COMPLETED curl -s "https://api.segmind.com/v2/requests/$REQUEST_ID/status" \ -H "x-api-key: YOUR_API_KEY" # 3. Fetch the result curl -s "https://api.segmind.com/v2/requests/$REQUEST_ID" \ -H "x-api-key: YOUR_API_KEY" ``` ### Seedance 2.5 Flash food video generator > Behind the counter of a small bakery, a baker in a flour-dusted blue apron holds up a crusty sourdough loaf, looks into the camera and says warmly, "Fresh from the oven — still warm." Wooden shelves of bread behind him. Medium close-up, static camera. Quiet bakery ambience with a coffee machine hissing softly. No music, no subtitles. Output: https://segmind-resources.s3.amazonaws.com/output/seedance-2.5-flash-example-native-audio-dialogue-ebf093ae.mp4 ```bash # 1. Submit the request; the reply carries its request_id REQUEST_ID=$(curl -s -X POST "https://api.segmind.com/v2/seedance-2.5-flash" \ -H "x-api-key: YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Behind the counter of a small bakery, a baker in a flour-dusted blue apron holds up a crusty sourdough loaf, looks into the camera and says warmly, \"Fresh from the oven — still warm.\" Wooden shelves of bread behind him. Medium close-up, static camera. Quiet bakery ambience with a coffee machine hissing softly. No music, no subtitles.", "first_frame_url": "", "last_frame_url": "", "reference_images": [], "reference_videos": [], "reference_audios": [], "duration": 5, "resolution": "720p", "aspect_ratio": "16:9", "generate_audio": true, "seed": 42, "return_last_frame": false, "skip_moderation": false, "bitrate_mode": "standard" }' | jq -r .request_id) # 2. Check its status until it is COMPLETED curl -s "https://api.segmind.com/v2/requests/$REQUEST_ID/status" \ -H "x-api-key: YOUR_API_KEY" # 3. Fetch the result curl -s "https://api.segmind.com/v2/requests/$REQUEST_ID" \ -H "x-api-key: YOUR_API_KEY" ``` ## Usage Examples ### cURL ```bash curl -X POST "https://api.segmind.com/v1/seedance-2.5-flash" \ -H "x-api-key: YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Two players rally at speed across a blue table-tennis table in a school gymnasium: the white ball snaps back and forth over the net, each paddle clips it with a sharp hollow pock, and rubber-soled shoes squeak on the varnished floor as the camera tracks the volley from the side. Natural diegetic sound - the crack of each hit, the ball bouncing on the table, squeaking shoes, and the hollow echo of the hall.", "first_frame_url": "", "last_frame_url": "", "reference_images": [], "reference_videos": [], "reference_audios": [], "duration": 5, "resolution": "720p", "aspect_ratio": "16:9", "generate_audio": true, "seed": 42, "return_last_frame": false, "skip_moderation": false, "bitrate_mode": "standard" }' \ -o output.mp4 ``` ### Python ```python import requests import json url = "https://api.segmind.com/v1/seedance-2.5-flash" headers = { "x-api-key": "YOUR_API_KEY", "Content-Type": "application/json" } data = { "prompt": "Two players rally at speed across a blue table-tennis table in a school gymnasium: the white ball snaps back and forth over the net, each paddle clips it with a sharp hollow pock, and rubber-soled shoes squeak on the varnished floor as the camera tracks the volley from the side. Natural diegetic sound - the crack of each hit, the ball bouncing on the table, squeaking shoes, and the hollow echo of the hall.", "first_frame_url": "", "last_frame_url": "", "reference_images": [], "reference_videos": [], "reference_audios": [], "duration": 5, "resolution": "720p", "aspect_ratio": "16:9", "generate_audio": true, "seed": 42, "return_last_frame": false, "skip_moderation": false, "bitrate_mode": "standard" } response = requests.post(url, headers=headers, json=data) if response.status_code == 200: # Media models return the file itself; a JSON body carries the result instead. if response.headers.get("Content-Type", "").startswith("application/json"): print(json.dumps(response.json(), indent=2)) else: with open("output.mp4", "wb") as f: f.write(response.content) print("Saved output.mp4") else: print(f"Error: {response.status_code}") print(response.text) ``` ### JavaScript ```javascript import { writeFile } from 'node:fs/promises'; const response = await fetch('https://api.segmind.com/v1/seedance-2.5-flash', { method: 'POST', headers: { 'x-api-key': 'YOUR_API_KEY', 'Content-Type': 'application/json', }, body: JSON.stringify({ "prompt": "Two players rally at speed across a blue table-tennis table in a school gymnasium: the white ball snaps back and forth over the net, each paddle clips it with a sharp hollow pock, and rubber-soled shoes squeak on the varnished floor as the camera tracks the volley from the side. Natural diegetic sound - the crack of each hit, the ball bouncing on the table, squeaking shoes, and the hollow echo of the hall.", "first_frame_url": "", "last_frame_url": "", "reference_images": [], "reference_videos": [], "reference_audios": [], "duration": 5, "resolution": "720p", "aspect_ratio": "16:9", "generate_audio": true, "seed": 42, "return_last_frame": false, "skip_moderation": false, "bitrate_mode": "standard" }), }); if (response.ok) { // Media models return the file itself; a JSON body carries the result instead. if ((response.headers.get('content-type') || '').startsWith('application/json')) { console.log(await response.json()); } else { await writeFile('output.mp4', Buffer.from(await response.arrayBuffer())); console.log('Saved output.mp4'); } } else { console.error('Error:', response.status); console.error(await response.text()); } ``` ### JavaScript (SDK) ```javascript // npm install segmind // export SEGMIND_API_KEY="YOUR_API_KEY" import { InferenceFailed, InferenceTimeout, Segmind } from 'segmind'; const segmind = new Segmind(); // reads SEGMIND_API_KEY // Async (v2) — recommended for long-running / video models. // run() waits up to 10 minutes; submit + job.wait({ timeout }) sets a longer // deadline and keeps the requestId so you can check again later. const job = await segmind.submit('seedance-2.5-flash', { "prompt": "Two players rally at speed across a blue table-tennis table in a school gymnasium: the white ball snaps back and forth over the net, each paddle clips it with a sharp hollow pock, and rubber-soled shoes squeak on the varnished floor as the camera tracks the volley from the side. Natural diegetic sound - the crack of each hit, the ball bouncing on the table, squeaking shoes, and the hollow echo of the hall.", "first_frame_url": "", "last_frame_url": "", "reference_images": [], "reference_videos": [], "reference_audios": [], "duration": 5, "resolution": "720p", "aspect_ratio": "16:9", "generate_audio": true, "seed": 42, "return_last_frame": false, "skip_moderation": false, "bitrate_mode": "standard" }); console.log(job.requestId); // available immediately try { const result = await job.wait({ timeout: 15 * 60_000, interval: 2_000 }); console.log(result.output); // model output (e.g. video URL) } catch (err) { if (err instanceof InferenceTimeout) console.log('still running:', err.requestId); else if (err instanceof InferenceFailed) console.log('failed:', err.detail); else throw err; } ``` ## Additional Resources ### Documentation - [Model Playground](https://www.segmind.com/models/seedance-2.5-flash) - [API Documentation](https://www.segmind.com/models/seedance-2.5-flash/api) - [Pricing Details](https://www.segmind.com/models/seedance-2.5-flash/pricing) - [Platform Documentation](https://docs.segmind.com/)