Models
Learn about latest models, changelog, and deprecations.
Soniox Speech-to-Text provides multiple models for real-time and asynchronous transcription and translation. This page lists the currently available models, their capabilities, and important updates.
Current models
Model | Type | Status | Key Features |
|---|---|---|---|
| stt-rt-preview-v2 | Real-time | Active | Higher transcription accuracy, better translation quality, and more reliable language switching. Supports all translation pairs |
| stt-async-preview-v1 | Async | Active | Asynchronous file-based transcription and translation |
Aliases
Aliases provide a stable reference so you don’t need to change your code when newer versions are released.
| Alias | Points to | Notes |
|---|---|---|
| stt-rt-preview | stt-rt-preview-v2 | Always points to the latest real-time preview model |
| stt-async-preview | stt-async-preview-v1 | Always points to the latest async preview model |
Changelog
August 15, 2025
- ❌ Deprecated
stt-rt-preview-v1
August 5, 2025
- 🚀 Released
stt-rt-preview-v2- Higher transcription accuracy
- Improved translation quality
- Expanded to support all translation pairs
- More reliable automatic language switching
Deprecations
| Model | Deprecation Date | Replacement |
|---|---|---|
| stt-rt-preview-v1 | August 15, 2025 | Use stt-rt-preview-v2 |
Deprecated models may stop working without notice. Always use the aliases (stt-rt-preview, stt-async-preview) for long-term stability.