Real-time streaming speech-to-text model for voice agents in 60 languages.
Released
Oct 1, 2026
Context window
Not disclosed
Max output
Not disclosed
Parameters
Not disclosed
Input price
Not disclosed
Output price
Not disclosed
Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.
Pricing
Launch priceOct 1, 2026
$0.0002 per second
Current price
since Oct 1, 2026
$0.0002 per second
Specifications
- Developer
- Microsoft
- Model type
- Other
- Architecture
- Not disclosed
- Parameters
- Not disclosed
- Input
- Audio
- Output
- Text
- Knowledge cutoff
- Not disclosed
- License
- Proprietary
- API access
- First-party API