Loading model…正在加载模型详情…
Loading model…正在加载模型详情…
Create short scenes from text with ByteDance’s Seedance 1.5 Pro, an audio-video model built around cinematic camera direction and expressive storytelling.
Medium shot, premium cinematic realism. Inside a lively Portuguese tavern, a middle-aged bartender warmly greets customers in English: "Welcome, friends! What can I get for you?" The customers reply, "We want a jug of beer and some snacks. And don't forget the olives, please!" The bartender nods, "Absolutely, right away!"
The camera slowly zooms in on the small lychee at the very top, which sways its body and says the promotional slogan in cute Sichuan dialect
A girl is at a music venue playing the drums
Seedance 1.5 Pro is ByteDance’s audio-video generation model. ByteDance’s description highlights cinematic camera direction, synchronized sound and expressive character scenes.
On UniRoute, the model accepts a text prompt with a resolution and duration option. Describe the scene and camera movement, select an option and review its quote before submitting a generation request.
Seedance 1.5 Pro is a later entry in ByteDance’s Seedance line. ByteDance’s description emphasizes generating visuals and audio together, with dialogue and emotional expression as central parts of the scene.
What you can do with Seedance 1.5 Pro through UniRoute today.
Write a shot description with the setting, characters, actions and camera movement. Choose a resolution and duration combination, then submit the quoted request.
Other Seedance 1.5 Pro modes (image-to-video and first and last frame controls) are not available on UniRoute yet; the current inputs are a text prompt and an output option, with no reference or audio controls.
The variants you can call, with their options and prices.
| Variant | Model ID | Modes | Inputs | Output | Price |
|---|---|---|---|---|---|
| Seedance 1.5 Pro | bytedance/seedance-1.5-pro | Text to video | Text prompt and a size option | Resolution: 480p, 720p, 1080p; Duration: 5s, 10s | $0.05 to $0.47 per request |
Priced per request. The option you choose sets the price.
| Seedance 1.5 Pro | |
|---|---|
| 480p · 5s | $0.05 |
| 480p · 10s | $0.11 |
| 720p · 5s | $0.11 |
| 720p · 10s | $0.22 |
| 1080p · 5s | $0.23 |
| 1080p · 10s | $0.47 |
Rounded to the cent; the live quote in the workspace shows the exact amount. Prices updated 2026-11-08.
Pay as you go from a single USD wallet balance. You see the quote before each request.
Call Seedance 1.5 Pro from your own code with the media API.
# Requires bash, curl and jq. Set API_KEY to your own unified UniRoute Key.set -euo pipefail: "${API_KEY:?Set API_KEY first}"BASE='https://api.uniroute.app/v1/media'MODEL='bytedance/seedance-1.5-pro'OPTION='480p:5'PROMPT='A calm sunrise over a mountain lake'curl -fsS --max-time 60 "$BASE/catalog" -H "Authorization: Bearer $API_KEY" | jq -e '.data.models'BODY=$(jq -n --arg model "$MODEL" --arg option "$OPTION" --arg prompt "$PROMPT" '{model:$model,option:$option,prompt:$prompt}')QUOTE_BODY=$(printf '%s' "$BODY" | jq '{model,option}')QUOTE=$(curl -fsS --max-time 60 "$BASE/quote" -H "Authorization: Bearer $API_KEY" -H 'Content-Type: application/json' -d "$QUOTE_BODY")CAP=$(printf '%s' "$QUOTE" | jq -er '.data.quoted_usd')BODY=$(printf '%s' "$BODY" | jq --arg cap "$CAP" '. + {max_cost_usd:$cap}')IDEMPOTENCY="example-$(date +%s)-$$"create() { curl -fsS --max-time 60 "$BASE/tasks" -H "Authorization: Bearer $API_KEY" -H "Idempotency-Key: $IDEMPOTENCY" -H 'Content-Type: application/json' -d "$BODY"; }TASK_ID=$(create | jq -er '.data.task_id')# The same request and idempotency key must return the original task without charging again.REPLAY_ID=$(create | jq -er '.data.task_id')[ "$TASK_ID" = "$REPLAY_ID" ]for attempt in $(seq 1 120); do TASK=$(curl -fsS --max-time 60 "$BASE/tasks/$TASK_ID" -H "Authorization: Bearer $API_KEY") printf '%s' "$TASK" | jq -e '.data | {task_id,status,billing}' if printf '%s' "$TASK" | jq -e '.data.status == "success" and .data.billing.state == "charged"' >/dev/null; then index=0 while IFS= read -r url; do index=$((index+1)) curl -fL --max-time 120 "$url" -o "$TASK_ID-$index.bin" done < <(printf '%s' "$TASK" | jq -er '.data.urls[].url') break fi if printf '%s' "$TASK" | jq -e '.data.status == "failed" and .data.billing.state == "released"' >/dev/null; then exit 1; fi if [ "$attempt" = 120 ]; then echo "Polling limit reached. Keep task ID $TASK_ID and query it later; do not create a new task." >&2 exit 1 fi sleep 5donecurl -fsS --max-time 60 "$BASE/tasks?limit=20" -H "Authorization: Bearer $API_KEY" | jq -e '.data'# Check this task and the caller Key in Console usage; billing.charged_usd is the actual USD charge.| Name | In | Description |
|---|---|---|
model | Body | Model ID to run. |
option | Body | One of the options offered for the model: 480p:5, 480p:10, 720p:5, 720p:10, 1080p:5, 1080p:10. |
prompt | Body | Text prompt describing what to generate. |
max_cost_usd | Body | Maximum cost in USD for this task, taken from the quote. |
Idempotency-Key | Header | A unique key per task, so a repeated request returns the original task instead of charging again. |
Typical ways to put Seedance 1.5 Pro to work.
Sketch a conversation or character moment in a written prompt and review it as a moving scene before committing to production.
Try visual directions for a product story or campaign using prompts that describe the setting, mood and camera movement.
Add text-to-video generation to an application with the media API, showing the quote before submitting each task.
Common questions about Seedance 1.5 Pro.
Seedance 1.5 Pro is ByteDance’s audio-video generation model. On UniRoute, you can use a text prompt and an output option to create video in the browser or through the media API.
Not currently. The UniRoute catalog exposes a text prompt and a resolution and duration option. It does not expose reference images, first or last frame inputs, or an audio switch.
Describe the scene, who is in it, what happens and how the camera moves. ByteDance’s description also discusses dialogue and sound within the scene; UniRoute does not provide separate audio parameters.
From $0.05 / clip. Requests are priced for the whole clip according to the selected option. See the Pricing section for every option and rate (prices updated 2026-11-08).
Use the media API to quote the selected model and option, create a task with an Idempotency-Key and a maximum cost, then poll its status until the video is ready. The API section includes a complete request example.
No. Generation is paid from your wallet balance. You can open the workspace and review the price without paying, create an account to see a live quote for your exact settings, and you are charged only for requests that are accepted.