Does Seedance audio cost extra on Sume? generate_audio and the price
Seedance prices on Sume are per video token and carry no separate audio line. What generate_audio does, what it defaults to, and the 10 s price either way.
No separate audio charge appears in Sume's Seedance estimate: a 10 s 720p Seedance 2.5 clip is $5.778 whether you set generate_audio to true or false. The estimator takes only resolution, aspect ratio, duration and any reference video into account.
The field itself is documented on Video generation: generate_audio tells the model to generate audio with the video or not, and its default is the audio capability of the model. The docs' example listing for seedance-2 shows generate_audio: true.
Same clip, both settings
| Model id | generate_audio omitted | true | false |
|---|---|---|---|
| seedance-2.5 | $5.778 | $5.778 | $5.778 |
| seedance-2 | $3.78 | $3.78 | $3.78 |
| seedance-2-fast | $3.024 | $3.024 | $3.024 |
| seedance-2-mini | $1.89 | $1.89 | $1.89 |
What does change the price
Resolution, aspect ratio and duration set the video-token count, and a reference video changes the multiplier. That is why the same 10 seconds is $1.89 on seedance-2-mini and $5.778 on seedance-2.5 at 720p: the tier changes the per-token rate, not the audio flag. For Seedance you are choosing whether the track exists, not what the clip costs.
Request with audio off
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"seedance-2.5","prompt":"Slow pan over a ceramic studio","duration":10,"resolution":"720p","generate_audio":false}'Practical
If you plan to lay your own music and voice over the clip, send false so you do not carry a track you will replace. Sume's audio detach tool can also split an existing track off later.
Sources
Related posts
More in Developers
- Draft on Grok Imagine, finish on Seedance 2.5: two calls, one prompt
A Python flow that renders a prompt on grok-imagine-video-1.5 for $0.125, then re-sends the approved text to seedance-2.5 at 1080p for $14.22.
- Elixir Req: submit and poll a Sume video job after Sora
An Elixir script using Req: POST /v1/videos with an Idempotency-Key, poll every 30 seconds, stop on completed, failed or cancelled. Req never retries the POST.
- Env and secrets diff for removing Sora: SUME_API_KEY, one auth header
Which environment variables to delete, add and rotate when a service leaves the OpenAI Videos API for Sume, plus a startup check that fails on a missing secret.
- Extract 16 kHz mono audio from a video for transcription
A Python script that detaches speech-ready 16 kHz mono wav from a Sume-hosted video, then polls the job. Costs $0.01 per detach before the STT minute.
Written by Sume