ByteDanceSeed Speech
Seed TTS 1.0
Seed TTS 1.0 remains an explicit resource option in the current synthesis API. It uses a different resource ID from TTS 2.0.
Technical guide
The API identifies timestamp controls separately for first- and second-generation voices. Version-specific parameters should be selected with the voice resource.Seed speech synthesis and voice replication API
Practical use
Practical guidance. For an existing subtitle workflow, compare timestamp alignment before switching versions. A successful audio response does not prove that the subtitle timing is equivalent.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | seed-tts-1.0volc.service_type.1000009 |
| Timestamps | Word and phoneme timestamps are documented for Chinese and English voices.Seed speech synthesis and voice replication API |
Related models
- Seed TTS 2.0
ByteDance ยท Seed Speech
Context-aware speech synthesis model with text controls for tone, emotion and pace.
Launch date not confirmedAPI