Seedance 2.5 · Text to Video With Audio

ABOUT THE WORKFLOW

Build a Clip From Words Write a prompt describing the scene, the action, the camera, and the sound. Seedance 2.5 builds the picture and the audio together in one pass and returns a finished clip. No image input needed.

Partner node. This workflow calls an external API, so each run uses credits from your API wallet. No API key needed. Floyo handles the connection.

Model

• Seedance 2.5 by ByteDance. Announced 23 June 2026 at the Volcano Engine FORCE conference and launched publicly 31 July 2026. The flagship of the Seedance video family. Generates native single-shot clips up to 30 seconds at up to 4K with sound in one pass. Accepts up to 50 multimodal reference inputs, though this workflow uses prompt only.

HOW IT WORKS

Step 1. Write your prompt Describe the scene, the action, the camera, and the sound. Long, layered prompts are followed closely. Works great with: cinematic scenes · product spots · mood films · social clips

Step 2. Pick a shape and length Choose an aspect ratio and a duration. Both settings drive what a run costs.

Step 3. Hit run and download The clip comes back as an MP4 with sound, saved under video/Seedance2.5. Ready for: Premiere · DaVinci Resolve · CapCut · After Effects

First time? Leave every setting as-is. The defaults (720p · 5 seconds · 16:9 · audio on · MP4) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

• Standard clip (most people) — 720p · 5 seconds · 16:9 · audio on · MP4. The right starting point for almost everyone.

• Need a longer clip — Raise the duration. Seedance 2.5 handles up to 30 seconds in a single pass with no stitching. Duration drives cost.

• Need a different shape — Switch the aspect ratio. Landscape, portrait, and square are all available from the dropdown.

• Sound is not matching the action — Describe the sound separately in the prompt after the visual action. Name the room tone, effects, and score as their own lines.

• The clip looks generic — Add more detail. Name the lighting, the time of day, the camera speed, and the texture of surfaces. Short vague prompts return short generic clips.

• Want the clip without sound — Turn audio off. The model skips the audio pass entirely.

• Want a different file format — Switch the output format away from MP4.

Prompt: Write it as a timeline. Subject and setting first, then what happens: "A street musician plays violin on a foggy bridge at dawn." Then camera: "slow crane up, wide to medium." Then sound: "birds call in the distance, strings echo off the water." Splitting the brief this way gives the model a clear read on what to show, how to move, and what to play.

LEARN

📹 Videos

• Intro to Floyo

• ComfyUI 101 Free Course ft. Sebastian Kamph

• Floyo 101 for Team Collaboration

✨ Quick links

• Help docs

• LoRA Training guide

• Discover more workflows

USE CASES

🎬 Short Films and Trailers Generate a 30-second continuous scene with camera moves, dialogue, and a score in a single pass.

📢 Ads and Product Spots Build a finished spot from a text brief without a shoot, a sound session, or separate audio work.

📱 Social Content Turn a one-line idea into a ready-to-post clip with matching sound for Reels, TikTok, or Shorts.

🎨 Previz and Mood Films Test how a scene plays before committing to a production schedule, a camera day, or an animation pass.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Detailed prompts with subject, camera, and sound described separately

• Steady camera work named in the prompt

• Clips of 5 to 15 seconds as a starting range

• Scenes with one or two clear subjects

⚠️ May produce softer results

• Short keyword prompts with no camera or sound direction

• Fast collisions or complex physics

• Clips pushed to 30 seconds on a first test without iteration

• Expecting precise lip-synced dialogue from text alone

FAQ

What is Seedance 2.5? Seedance 2.5 is ByteDance's flagship video model, announced 23 June 2026 at the Volcano Engine FORCE conference and launched 31 July 2026. It generates native single-shot clips up to 30 seconds at up to 4K with synchronized audio in one pass. It supports text to video, image to video, and reference to video, and accepts up to 50 multimodal reference inputs in a single generation.

Does Seedance 2.5 generate audio with the video? Yes. Sound is generated in the same pass as the picture, so effects, room tone, and background music land on the same timeline as the action. Describe the sound in your prompt and it goes onto the track. Turn audio off if you want a silent clip.

How long can a Seedance 2.5 clip be? Up to 30 seconds in a single pass with no stitching, which is roughly double the 15-second ceiling of most prior models. A separate ultra-long beta mode extends to 180 seconds through ByteDance's own apps, though that is not available through this endpoint.

Is Seedance 2.5 open source? No. Seedance 2.5 is a closed model with no published weights. It is reached through the ByteDance Seed API. Seedance 2.0 is available on some third-party platforms, but the weights themselves have never been released publicly for any version.

What is the difference between Seedance 2.5 and Seedance 2.0? Seedance 2.5 doubles the clip length from 15 to 30 seconds, adds support for up to 50 multimodal references in one generation, and introduces region-level editing that changes part of a frame without regenerating the whole clip. Seedance 2.0 received a separate 4K upgrade alongside the 2.5 announcement.

How does Seedance 2.5 compare to Wan 2.7 and MiniMax H3? All three generate video with native audio. Seedance 2.5 leads on clip length at 30 seconds and on reference count at 50 inputs. Wan 2.7 adds a thinking mode that plans composition before rendering and goes up to 15 seconds. MiniMax H3 is the only one with open weights and handles up to 15 seconds at 768p with audio. Pick Seedance 2.5 for the longest single-pass clips, Wan 2.7 for compositional planning, and H3 for open weights.

How to run Seedance 2.5 online? You can run Seedance 2.5 online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, write a prompt, and hit run. Free to try.

WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A designer runs an edit and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.

Ready to try it? Write a prompt and run it. The clip comes back with sound.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.