Voiceprint Models
Voiceprint models are extractors of the biometric characteristics of the voice. They can be used to compute voiceprints.
Version selection: the platform automatically selects the latest versions of verification models.
Model Descriptions
Model Name | Handle | Version | Status | Description |
---|---|---|---|---|
Digital | digital | v1 | ✅ Available | The digital voiceprint model is specifically designed and trained for managing higher quality audio, with sample rates of 16KHz or higher. The English and Spanish languages make up a significant part of its training dataset. |
Phone | phone | v1 | ✅ Available | The phone voiceprint model is specifically designed and trained for managing phone audio, with sample rates of 8KHz or higher. The telephone channel and the English and Spanish languages make up a significant part of its training dataset. |
Default | default | v1 | ⚠️ Deprecated | The default voiceprint model is deprecated and will be removed in a future platform release. |
Model Requirements
Model Name | Audio Max Duration | Audio Min Voice Duration | Audio Min Frequency | Voiceprint Max Total Duration | Voiceprint Min Total Voice Duration | State |
---|---|---|---|---|---|---|
Digital | 2 minutes | 4.5 seconds / minimum audios | 16000 Hz | 2 minutes | 4.5 seconds | Computable |
Phone | 2 minutes | 4.5 seconds / minimum audios | 8000 Hz | 2 minutes | 4.5 seconds | Computable |
Default | 2 minutes | 4.5 seconds / minimum audios | 16000 Hz | 2 minutes | 4.5 seconds | Computable |