ByteDance
Seedance 2.5 Flash
seedance-2.5-flash/text-to-video
The ByteDance Seedance 2.5 series video model supports text-to-video, first-frame-based generation, and multimodal reference generation, producing 4 to 30 seconds per output with a choice of 480p or 720p and synchronized audio, making it ideal for rapidly producing short advertising clips and e-commerce product videos
Try seedance-2.5-flash/text-to-video
Input
Showcases
View all showcasesOutput
videoPricing
seedance-2.5-flash/text-to-video per second
| Specifications | Unit Price |
|---|---|
| 480P | $0.0679 |
| 720P | $0.1525 |
Positioning Overview
This is a text-to-video model: simply enter a text prompt and it generates a continuous video clip with an audio track. You can set the duration from 4 to 30 seconds, choose 480p or 720p resolution, and select a frame ratio from 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, or adaptive, with output in MP4 or MOV. By default it generates synchronized dialogue, sound effects, and background audio. It is aimed at creators in advertising, e-commerce, social media, and narrative shorts, for quickly turning creative copy into deployable video assets.
Core Highlights
- Prompt-to-video with an audio track — by default it generates synchronized dialogue, sound effects, and background audio, reducing the need for post-production audio work.
- Single-generation duration from 4 to 30 seconds — the duration parameter can be set between 4 and 30 seconds, suitable for a complete short video or an advertising shot.
- Seven frame ratios with adaptive option — supports 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, and adaptive, covering landscape, square, and portrait.
- Dual resolution: 480p and 720p — choose 480p or 720p output resolution to balance fast previews and clearer final footage.
Capability Description
Text-prompt-to-video: Enter a prompt of up to 5000 characters describing the scene, subject, camera movement, and action to generate the corresponding video clip; prompts should be specific to improve predictability.
Duration and resolution control: A single request can set a duration of 4 to 30 seconds, with resolution chosen from 480p or 720p; billing is based on the requested duration.
Multiple frame ratios and adaptive: Choose a frame ratio of 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, or adaptive; adaptive lets the model choose a suitable ratio based on the prompt.
Synchronized audio generation: Audio generation is enabled by default, producing synchronized dialogue, sound effects, and background audio along with the visuals; you can also turn audio off to output visuals only.
MP4 and MOV output: Choose MP4 or MOV output format; MP4 is the compatible default, while MOV is for professional post-production workflows.
Applicable Scenarios
- Advertising teams generating brand shorts from copy — enter a prompt containing the opening, camera movement, action, and ending to generate a 4-to-30-second video with an audio track, for ad delivery or pitch previews.
- E-commerce operators generating product showcase shots — describe the product's appearance and usage scenario in text, choose a square or portrait frame ratio, and produce short-video assets for product detail pages or feeds.
- Social media creators batch-producing vertical content — use a 9:16 or 1:1 frame ratio with a duration under 30 seconds to turn creative copy into short videos with sound effects, for daily platform updates.
- Narrative short-film authors generating continuous shots — use detailed prompts to describe multiple characters and scene actions, generating a continuous clip of up to 30 seconds in a single run, for story segments in short content.
Limitations and Selection Advice
The maximum duration for a single generation is 30 seconds; longer content must be generated in segments and then stitched together. Output resolution is only 480p or 720p, with no higher clarity offered. The frame ratio is one of seven choices; you cannot get multiple ratios in a single request. Prompts are capped at 5000 characters; anything longer must be trimmed. When audio generation is turned off, the output video has no audio track; when audio is enabled by default, synchronized dialogue, sound effects, and background audio are generated along with the visuals.
Text-to-video · Up to 30 seconds · 480p/720p
seedance-2.5-flash Text-to-Video
Enter a text prompt to generate a continuous video clip with an audio track. Duration, resolution, frame ratio, and output format can all be set as needed, making it suitable for quickly producing advertising, e-commerce, social media, and narrative short videos.
- InputText prompt
- Duration range4–30 seconds
- Resolution480p / 720p
- Output formatMP4 / MOV
The more specifically the prompt describes the scene, subject, camera movement, and action, the more predictable the generated result.
A quiet old fishing harbor at dawn wrapped in thin sea fog. The camera starts low near wet stone steps where seawater slides up and recedes in slow rhythmic sheets, foam threading between the cracks; it then drifts forward and slightly upward along the quay, past coiled ropes and rusted mooring rings, toward small wooden boats rocking gently against their lines. A fisherman in a faded oilskin bends to pull a rope, his breath visible. In the distance a lighthouse lamp pulses softly through the fog, and gulls skim low over the water. Grey-blue light gradually warms to pale gold as the fog thins, revealing wet surfaces glistening with reflections. Steady floating movement, unhurried pacing, shallow depth in the foreground, soft mist diffusion and natural sea sound atmosphere.
01
Capabilities
How it performs: four verifiable capabilities
All of the following capabilities take a text prompt as input; the key is to verify whether duration, resolution, frame ratio, and the audio toggle meet your targets.
Text-prompt-to-video
Use a text description of the scene, subject, camera movement, and action, and the model generates a video clip accordingly. The prompt limit is 5000 characters; it is recommended to state the key visual elements clearly so you can check whether the visuals match the description.
A lone ice climber in a red shell jacket ascends a frozen blue waterfall with two ice axes, breathing visible in the cold air. The camera tracks close along the ice wall, slightly above him, catching shards of ice spinning away from each axe strike. A low rumble rolls across the ridge, and a plume of snow dust pours over the cliff top, growing fast. The climber glances up, then moves laterally with quick, deliberate swings, traversing out of the falling snow's path as the white surge sweeps past the ice behind him. Cold daylight, deep blue shadows inside the ice, grainy wind-driven snow particles, steady handheld urgency that settles into a wider reveal of the mountain face at the end.
Duration and resolution settings
A single request can set a duration between 4 and 30 seconds and choose a resolution of 480p or 720p. Billing is based on the requested duration; before generating, first confirm the duration and clarity required for the intended use of the final footage.
Multiple frame ratios and adaptive ratio
Frame ratios support 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, and adaptive. With adaptive, the model chooses the ratio based on the prompt, which suits the exploration stage when the delivery layout has not yet been decided.
Audio generation and format selection
By default, synchronized dialogue, sound effects, and background audio are generated along with the visuals, but this can be turned off. Output format can be MP4 or MOV; the former is compatible with common playback and sharing, while the latter is for professional post-production workflows.
With a clear text description and explicit duration, frame ratio, and resolution parameters, you can obtain a video clip with an audio track; after generation, focus on checking how well the visuals match the prompt and the state of the audio toggle.
02
Getting Started
From text description to finished video
Try it →From clarifying the goal to generating and reviewing, set the input and parameters step by step, adjusting one category of content at a time.
- Prompte.g.: sunset by the sea, a person walking along the beach, camera slowly following
A complete text description
01
Write a specific prompt
In the prompt, clearly state the scene, subject, camera movement, and action, keeping it within 5000 characters. The more specific the description, the more predictable the result.
✓Verify
→
02
Set duration and frame ratio
Choose a duration of 4 to 30 seconds based on the use case and specify 480p or 720p resolution; select landscape, portrait, square, or adaptive frame ratio according to the delivery platform.
✓Verify
→
03
Choose audio and output format
Confirm whether to generate audio; output format can be MP4 or MOV. After generation, check how well the visuals match the prompt and whether an audio track is present.
03
Scenarios
Where it's used: three typical short videos
Brand shorts and ad previews
Advertising teams use a text prompt containing the opening, camera movement, action, and ending to generate a short video with an audio track, for pre-delivery previews or pitches. Focus on checking whether the visual pacing and audio are synchronized.
E-commerce product showcase shots
E-commerce operators describe a product's appearance and usage scenario in text, choose a square or portrait frame ratio to generate a short video for product detail pages or feed assets, and check whether the product's appearance matches the description.
Social media vertical short videos
Creators use a 9:16 or 1:1 frame ratio and a duration under 30 seconds to generate short videos with sound effects for daily platform updates; after generation, confirm that the frame ratio matches platform requirements and that the audio toggle meets your needs.
04
Integration
Integration: Call seedance-2.5-flash in your product or AI tool
A single HiAPI API Key is all you need; all methods share the same account and billing.
- Create an API Key
- Choose an integration method
Pick any one on the right and copy it
- AI coding tools Recommended
Connect via MCP using commands for Claude Code, Cursor, Codex, etc.
- Direct API
Your own product, backend services, automation workflows
- Not sure which to choose
Copy a message to your AI and let it choose for you and provide the steps
Terminal · Claude Code
claude mcp add --transport http hiapi https://mcp.hiapi.ai/mcp \
--header "Authorization: Bearer YOUR_API_KEY"Once connected, simply tell the AI your goal and let it call seedance-2.5-flash, check task progress, and get the results. For configuration steps in tools like Cursor and Codex, see the tutorial below.
View the Agent integration tutorial →Integrate into your product via API
Use the API Key to submit a task for the current model, and query the status using the returned task ID. The request parameters use the same route data as the API description on this page; please replace the sample input content with your actual materials.
# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
-H "Authorization: Bearer $HIAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.5-flash/text-to-video",
"input": {
"prompt": "…",
"duration": 5,
"resolution": "480p",
"aspect_ratio": "adaptive",
"output_format": "mp4",
"generate_audio": true
}
}'Let AI help you choose an integration method
Please read the HiAPI documentation index at https://hiapi.ai/llms.txt. I want to use seedance-2.5-flash in my project. First, based on my use case, determine whether Remote MCP, Agent Skills, or a direct API is appropriate; if necessary, ask me one key question first, then provide the simplest integration steps and the configuration to fill in.
Copy this message and send it to the AI tool you use, then add your project language, input materials, and expected results. It can then explain the integration method and next steps accordingly.
What's new
View changelog →- New model seedance-2.5-flash/reference-to-video is live
- New model seedance-2.5-flash/image-to-video is live
- New model seedance-2.5-flash/text-to-video is live
Frequently asked questions
View all FAQs →-
What is the maximum length of a video that can be generated from an image?
A single generation can be set to a maximum of 30 seconds, a minimum of 4 seconds, and defaults to 5 seconds. The duration field directly determines the length and is also billed by the requested duration; for longer finished videos, you can only generate segments and stitch them together.
-
How do I set the duration, and how is it billed?
Set duration to a whole number of seconds from 4 to 30; the default is 5. Reference-to-video also accepts -1, which lets the model choose the length. All three routes are billed on the seconds of video delivered, at a different rate for 480p and 720p. Reference images and audio do not add billable seconds. A fixed duration is billed as requested; with -1 you pay for the delivered clip's length rounded to the nearest second, with a 4-second minimum. Use a fixed duration if you need a predictable bill.
-
Which resolutions and aspect ratios are supported?
There are two resolutions, 480p and 720p, with 480p as the default. Text-to-video and reference-to-video accept 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, or adaptive to let the model decide. Image-to-video is always adaptive and follows the first frame, so upload a portrait first frame if you want 9:16. This model does not offer 1080p.
-
What are the requirements for uploaded images and audio?
For image-to-video, first and last frames can be jpeg, png, webp, bmp, tiff, gif, heic or heif, under 30 MB, 300 to 6000 pixels per side, with an aspect ratio between 0.4 and 2.5. A last frame with a different ratio is center-cropped to match. Reference-to-video takes up to 10 reference images in the same formats except heic, heif and svg, and up to 5 audio clips in wav or mp3, each under 15 MB and 2 to 30 seconds, 30 seconds combined. Audio can be used without any image.
Create a generation task
https://api.hiapi.ai/v1/tasks Headers
AuthorizationstringRequiredAccount API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key
Content-TypestringOptionalThe request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.
Idempotency-KeystringOptionalIdempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.
On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.
Body
modelstringRequiredCurrent fixed value: seedance-2.5-flash/text-to-video
routestringOptionalCurrent fixed value: default
inputobjectRequired
Business parameters for seedance-2.5-flash/text-to-video and route default — see the parameter table below.
promptstringRequiredminLength 1maxLength 5000Text prompt describing the video content you want to generate; the more specific the description of the scene, subjects, camera motion, and action, the more predictable the generated result.
durationintegerOptionalDefault: 5min 4max 30Output video duration in seconds, ranging from 4 to 30, default 5; billing is calculated based on the requested duration.
resolutionstringOptionalDefault: "480p"Output resolution. Seedance 2.5 Flash supports 480p and 720p, default 480p.
480p720paspect_ratiostringOptionalDefault: "adaptive"Output aspect ratio, default adaptive, meaning the model automatically selects a suitable ratio based on the prompt.
16:94:31:13:49:1621:9adaptiveoutput_formatstringOptionalDefault: "mp4"Output file format, default mp4 (a versatile choice with better compatibility); mov is suitable for professional post-production.
mp4movgenerate_audiobooleanOptionalDefault: trueWhether to generate audio, including dialogue synchronized with the visuals, sound effects, and background audio; default true.
callbackobjectOptional
Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.
Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.
urlstringRequiredRequired when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.
whenstringOptionalDefault: "final"Only final is supported today — notified on both success and fail.
finalstoragestringOptionalDefault: "temp"Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.
temppersistentRequest examples
# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
-H "Authorization: Bearer $HIAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.5-flash/text-to-video",
"input": {
"prompt": "…",
"duration": 5,
"resolution": "480p",
"aspect_ratio": "adaptive",
"output_format": "mp4",
"generate_audio": true
}
}' const res = await fetch("https://api.hiapi.ai/v1/tasks", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "seedance-2.5-flash/text-to-video",
input: {
"prompt": "…",
"duration": 5,
"resolution": "480p",
"aspect_ratio": "adaptive",
"output_format": "mp4",
"generate_audio": true
}
}),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } } import os, requests
res = requests.post(
"https://api.hiapi.ai/v1/tasks",
headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
json={
"model": "seedance-2.5-flash/text-to-video",
"input": {
"prompt": "…",
"duration": 5,
"resolution": "480p",
"aspect_ratio": "adaptive",
"output_format": "mp4",
"generate_audio": True
}
},
)
print(res.json()) # { code, message, data: { taskId } } 200 OK
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
}
} 400 Bad Request
{
"code": 400,
"message": "invalid request",
"data": null,
"error_code": "INVALID_REQUEST"
} Get task detail
https://api.hiapi.ai/v1/tasks/:id Response fields
taskIdstringRequiredTask ID, always prefixed with tk-hiapi-.
modelstringRequiredResolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.
routestringOptionalPresent only when the task was submitted with an explicit route parameter; echoes the submitted value.
statusstringRequiredTask status.
queued Queued, not started yet.
handling Being processed.
archiving Processing finished, artifacts being prepared.
success Terminal: completed, artifacts available (output returned).
fail Terminal: failed (error returned).
After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.
creatednumberRequiredTask creation time (Unix seconds).
completednumberRequiredUnix seconds when the task reached a terminal state; fixed to 0 while not terminal.
outputarrayOptional
Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).
Array [ object ]
Array items
urlstringRequiredArtifact URL, directly downloadable.
typestringRequiredCurrent possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.
expireAtnumberRequiredUnix seconds until which the artifact remains accessible; download or transfer before it expires.
errorobjectOptional
Present only when status == fail.
codestringRequiredBusiness error code.
messagestringRequiredError description.
Response examples
Success
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
"model": "happyhorse-1-0",
"status": "success",
"created": 1777282033,
"completed": 1777282099,
"output": [
{
"url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
"type": "video",
"expireAt": 1777886899
}
]
}
} Processing (non-terminal)
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-...",
"model": "happyhorse-1-0",
"status": "archiving",
"created": 1777282033,
"completed": 0
}
} Failed
{
"code": 200,
"message": "success",
"data": {
"taskId": "tk-hiapi-...",
"model": "happyhorse-1-0",
"status": "fail",
"created": 1777282033,
"completed": 1777282099,
"error": {
"code": "TASK_FAILED",
"message": "task failed"
}
}
} Articles
View all articles →-
Guide
Seedance 2.5 Flash Text-to-Video: Parameters, Per-Second Billing and Production Practice
From the first request to a stable pipeline: how to set parameters and how the bill adds up
8 min read -
Guide
Seedance 2.5 Flash Image-to-Video: First Frame, Last Frame and Per-Second Billing
Making a still image move: parameters, price and the usual failure modes
7 min read -
Guide
Seedance 2.5 Flash Reference-to-Video: Reference Images, Audio and How the Bill Is Counted
9 min read
Related Models
View all models →Same Type
-
Veo 3.1 Fast Google $0.170 /second -
Gemini Omni 1.1 Google $0.450 /video -
Grok Imagine 1.5 xAI $0.011 /second -
Wan 3.0 Video Alibaba $0.040 /second -
Hailuo 2.3 MiniMax $0.270 /video -
Vidu Q3 Vidu $0.149 /second -
Wan 2.6 Flash Alibaba $0.043 /second -
LTX 2.5 Fast Lightricks $0.086 /second -
Grok Imagine 1.5 Lite xAI $0.029 /second -
HeyGen Avatar IV HeyGen $0.150 /second -
Vidu Q4 Preview Vidu $0.051 /second -
P-Video 2 Pro Replace Pruna AI $0.036 /second