Seed Audio 1.0 on OpenRouter: text to speech, and what Sume offers
ByteDance's Seed Audio 1.0 is listed on OpenRouter as text-to-speech with raw MP3 or PCM output. Sume's TTS Router is Cartesia Sonic only today.
ByteDance's Seed Audio 1.0 is listed on OpenRouter as a text-to-speech model that takes text and returns raw audio bytes in MP3 or PCM format. Sume's TTS Router does not carry it: its first catalog is Cartesia Sonic only, so a Seed Audio request has no Sume model id to point at.
What OpenRouter lists
Sources: OpenRouter ByteDance Seed models and Seed Audio 1.0, read 2026-10-02. The same listing shows Seedream image models; it does not list a Seedance video model.
| Item | What the page says |
|---|---|
| Model id | bytedance-seed/seed-audio-1-0 |
| Task | Text-to-speech |
| Input | Text |
| Output | Audio as MP3 or PCM, raw bytes, not JSON |
| Pricing and release date | Not stated on the model page |
What Sume's TTS Router offers
Sume's TTS Router docs list the seed catalog as Cartesia Sonic only: sonic-3.6, sonic-3.5, sonic-3, sonic-latest and sonic-preview. The docs say the router does not include Eleven, OpenAI or any other TTS family in v1, and that later vendors would be added as catalog rows.
The call is also different: POST /v1/tts-router/generate submits an async job, and you read the result from the job endpoints, not from a stream of bytes.
What to do if you want Seed Audio
If your project needs the Seed Audio voice, call it through the provider that lists it, and keep that audio separate from your Sume jobs. You can still bring the file into a Sume video workflow as an audio reference where a model accepts one; check supported_input_references for the model in GET /v1/videos/models first.
If you only need a good voice, Sonic through the router is the supported path.
- Keep the model id exactly as the vendor lists it.
- Do not assume a Sume id exists because a model is on another router.
- Check the Sume catalog before you write the integration.
The honest summary
Seed Audio is a recent addition to ByteDance's model family. Sume does not run it, and this page does not suggest otherwise.
Sources
Related posts
More in Models
- Seedance 2.5 concert prompt uses 18 images: fitting Sume's 9
Seed's Seedance 2.5 concert example uses 18 reference images. Sume's Video Router takes at most 9 for seedance-2.5, so merge groups into sheets.
- Seedance 2.5 on Dreamina: age 16+ and countries, what applies
Dreamina says Seedance 2.5 is for subscribers over 16 and names rollout regions. What the pages say, and where a developer account differs.
- Seedance 2.5 duration 3 seconds: 400 error, the minimum is 4
Seedance 2.5 on Sume takes 4 to 30 seconds. A 3-second request returns 400; a 31-second one is refused too. Here are the messages and the shorter-clip options.
- Seedance 2.5 on Jimeng or Doubao Pro: where the API fits
ByteDance launched Seedance 2.5 on Jimeng AI and Doubao Pro. If you need it from code, here is what Sume lists and what the vendor page says.
Written by Sume