ByteDance's most advanced text-to-video model, fast tier. Lower latency and cost with cinematic output, native audio, multi-shot editing, and director-level camera control.

bytedance/seedance-2.0/fast/text-to-video

ByteDance's most advanced text-to-video model, fast tier. Lower latency and cost with cinematic output, native audio, multi-shot editing, and director-level camera control.

Learn more about Seedance 2

Inference

Commercial use

Partner

Schema

LLMs

Playground API Examples

SandboxOpen in Sandbox

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

bytedance/seedance-2.0/fast/text-to-video

Schema

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Input

Prompt*

A hyper-realistic medium shot of two women in their late 20s to early 30s sitting cross-legged on opposite ends of a deep charcoal sectional sofa in a cozy, lived-in apartment during a lazy Sunday afternoon, captured with a handheld camera feel as if a third friend is casually filming them; the first woman has sleek jet-black hair pulled into a low ponytail with a few wispy baby hairs framing her face, warm olive skin, wearing a soft oatmeal cashmere cardigan over a white tank top and high-waisted black leggings, cradling a steaming mug of matcha in both hands and smiling softly as she says: "I finally booked the Lisbon trip this morning — I've been talking about it for two years and I just did it"; the second woman, with shoulder-length honey blonde waves and a light tan, wearing a rust-colored oversized hoodie and denim shorts, is sitting up straighter now with both hands raised in excitement, eyes wide as she replies: "Wait, seriously? Okay we're making a list right now, I know exactly where you need to eat"; between them sits a messy coffee table with an open laptop, two ceramic mugs, a half-eaten croissant on a small plate, scattered travel magazines, and a flickering vanilla candle, the background showing a small open kitchen with unwashed dishes in the sink, a fridge covered in magnets and photos, warm pendant lighting casting soft amber tones, a cat curled up on a nearby armchair barely visible in the bokeh, all rendered with natural skin texture including pores and slight blemishes, subtle motion blur on the gesturing hands, film grain, and muted warm color grading that feels like a candid moment from an Instagram close-friends story rather than anything staged.

Resolution

Duration

Generate Audio

End User Id

Additional Settings

Customize your input with more control.

For every second of 720p video you generated, you will be charged $0.2419/second. Your request will cost $0.0112 per 1,000 tokens. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024.

Result

Idle

What would you like to do next?

Download

{
  "seed": 1846092271,
  "video": {
    "url": "https://v3b.fal.media/files/b/0a959a2a/EaIW2xdGlq41Ab1codNXE_video.mp4",
    "file_name": "video.mp4",
    "file_size": 3738513,
    "content_type": "video/mp4"
  }
}

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Input

Prompt*

Resolution

Duration

Generate Audio

End User Id

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Download

{
  "seed": 1846092271,
  "video": {
    "url": "https://v3b.fal.media/files/b/0a959a2a/EaIW2xdGlq41Ab1codNXE_video.mp4",
    "file_name": "video.mp4",
    "file_size": 3738513,
    "content_type": "video/mp4"
  }
}

Run Seedance 2.0 AI Fast Text To Video API on fal

ByteDance's most advanced text-to-video model, available on fal as bytedance/seedance-2.0/fast/text-to-video.

Overview

The simplest Seedance 2.0 endpoint: provide a text prompt, get a fully produced cinematic video. No image or reference input required. The model handles camera direction, physics, multi-shot editing, and synchronized audio all in a single pass.

Key capabilities:

Native audio generation: music, SFX, and lip-synced dialogue, all included at no extra cost
Director-level camera control: dolly zooms, rack focuses, tracking shots, POV switches, handheld movement
Realistic physics: collisions, fabric, character motion, vehicle chases, fight scenes
Multi-shot editing: natural cuts within a single generation, up to 15 seconds
Cinematic 720p output

Parameters

Parameter	Type	Default	Description
`prompt`	string	—	Text description of the video to generate
`resolution`	enum	`720p`	`480p` (faster/cheaper) or `720p`
`duration`	enum	`auto`	`auto` or any integer from `4` to `15` seconds
`aspect_ratio`	enum	`auto`	`auto`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`
`generate_audio`	boolean	`true`	Synchronized audio: SFX, ambient sound, lip-synced speech. Same price either way.
`seed`	integer	—	Fix for reproducibility (minor variation may still occur)
`end_user_id`	string	—	Optional identifier for the end user

Pricing

Billed per second of generated 720p output:

Tier	Rate	10-sec clip
Fast tier	$0.2419 / sec	~$2.42
Standard tier	$0.3034 / sec	~$3.03
Token-based billing	$0.014 / 1,000 tokens	—

Token formula: tokens = (height × width × duration × 24) / 1024

Audio generation is included at no extra cost regardless of the generate_audio setting.

Quick Start

Python

bash
pip install fal-client
export FAL_KEY="YOUR_API_KEY"

python
import fal_client

result = fal_client.subscribe(
    "bytedance/seedance-2.0/fast/text-to-video",
    arguments={
        "prompt": "A lone astronaut walks across a rust-colored Martian plain at dusk, dust devils swirling in the distance, handheld camera, cinematic.",
        "resolution": "720p",
        "duration": "10",
        "aspect_ratio": "16:9",
        "generate_audio": True,
    },
    with_logs=True,
    on_queue_update=lambda u: [print(l["message"]) for l in u.logs]
    if isinstance(u, fal_client.InProgress) else None,
)

print(result["video"]["url"])

JavaScript / Node.js

bash
npm install @fal-ai/client
export FAL_KEY="YOUR_API_KEY"

js
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("bytedance/seedance-2.0/fast/text-to-video", {
  input: {
    prompt: "A lone astronaut walks across a rust-colored Martian plain at dusk, dust devils swirling in the distance, handheld camera, cinematic.",
    resolution: "720p",
    duration: "10",
    aspect_ratio: "16:9",
    generate_audio: true,
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});

console.log(result.data.video.url);

Output

json
{
  "video": {
    "url": "https://...",
    "content_type": "video/mp4",
    "file_name": "output.mp4",
    "file_size": 4823041
  },
  "seed": 42
}

Async / Queue Usage

python
handler = fal_client.submit(
    "bytedance/seedance-2.0/fast/text-to-video",
    arguments={...},
    webhook_url="https://your-server.com/webhook",
)

request_id = handler.request_id
status = fal_client.status("bytedance/seedance-2.0/fast/text-to-video", request_id, with_logs=True)
result = fal_client.result("bytedance/seedance-2.0/fast/text-to-video", request_id)

Choosing the Right Endpoint

All three fast-tier endpoints share the same schema and pricing. Choose based on your inputs:

Endpoint	When to use
`bytedance/seedance-2.0/fast/text-to-video`	Text prompt only, no reference media
`bytedance/seedance-2.0/fast/image-to-video`	Animate a single starting image, optionally with an ending frame
`bytedance/seedance-2.0/fast/reference-to-video`	Multi-modal: up to 9 images, 3 videos, and 3 audio clips as references

Run Seedance 2.0 AI Fast Text To Video API on fal

ByteDance's most advanced text-to-video model, available on fal as bytedance/seedance-2.0/fast/text-to-video.

Overview

Key capabilities:

Native audio generation: music, SFX, and lip-synced dialogue, all included at no extra cost
Director-level camera control: dolly zooms, rack focuses, tracking shots, POV switches, handheld movement
Realistic physics: collisions, fabric, character motion, vehicle chases, fight scenes
Multi-shot editing: natural cuts within a single generation, up to 15 seconds
Cinematic 720p output

Parameters

Parameter	Type	Default	Description
`prompt`	string	—	Text description of the video to generate
`resolution`	enum	`720p`	`480p` (faster/cheaper) or `720p`
`duration`	enum	`auto`	`auto` or any integer from `4` to `15` seconds
`aspect_ratio`	enum	`auto`	`auto`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`
`generate_audio`	boolean	`true`	Synchronized audio: SFX, ambient sound, lip-synced speech. Same price either way.
`seed`	integer	—	Fix for reproducibility (minor variation may still occur)
`end_user_id`	string	—	Optional identifier for the end user

Pricing

Billed per second of generated 720p output:

Tier	Rate	10-sec clip
Fast tier	$0.2419 / sec	~$2.42
Standard tier	$0.3034 / sec	~$3.03
Token-based billing	$0.014 / 1,000 tokens	—

Token formula: tokens = (height × width × duration × 24) / 1024

Audio generation is included at no extra cost regardless of the generate_audio setting.

Quick Start

Python

bash
pip install fal-client
export FAL_KEY="YOUR_API_KEY"

python
import fal_client

result = fal_client.subscribe(
    "bytedance/seedance-2.0/fast/text-to-video",
    arguments={
        "prompt": "A lone astronaut walks across a rust-colored Martian plain at dusk, dust devils swirling in the distance, handheld camera, cinematic.",
        "resolution": "720p",
        "duration": "10",
        "aspect_ratio": "16:9",
        "generate_audio": True,
    },
    with_logs=True,
    on_queue_update=lambda u: [print(l["message"]) for l in u.logs]
    if isinstance(u, fal_client.InProgress) else None,
)

print(result["video"]["url"])

JavaScript / Node.js

bash
npm install @fal-ai/client
export FAL_KEY="YOUR_API_KEY"

js
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("bytedance/seedance-2.0/fast/text-to-video", {
  input: {
    prompt: "A lone astronaut walks across a rust-colored Martian plain at dusk, dust devils swirling in the distance, handheld camera, cinematic.",
    resolution: "720p",
    duration: "10",
    aspect_ratio: "16:9",
    generate_audio: true,
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});

console.log(result.data.video.url);

Output

json
{
  "video": {
    "url": "https://...",
    "content_type": "video/mp4",
    "file_name": "output.mp4",
    "file_size": 4823041
  },
  "seed": 42
}

Async / Queue Usage

python
handler = fal_client.submit(
    "bytedance/seedance-2.0/fast/text-to-video",
    arguments={...},
    webhook_url="https://your-server.com/webhook",
)

request_id = handler.request_id
status = fal_client.status("bytedance/seedance-2.0/fast/text-to-video", request_id, with_logs=True)
result = fal_client.result("bytedance/seedance-2.0/fast/text-to-video", request_id)

Choosing the Right Endpoint

All three fast-tier endpoints share the same schema and pricing. Choose based on your inputs:

Endpoint	When to use
`bytedance/seedance-2.0/fast/text-to-video`	Text prompt only, no reference media
`bytedance/seedance-2.0/fast/image-to-video`	Animate a single starting image, optionally with an ending frame
`bytedance/seedance-2.0/fast/reference-to-video`	Multi-modal: up to 9 images, 3 videos, and 3 audio clips as references