Take a look at our ASR optimization guide and the model reference for available sizes and specs.
Speech Enhancement
Quail
Speech enhancement that improves Speech-to-Text accuracy for Voice AI.
The Quail models are purpose-built for Voice AI Agents and human-to-machine interactions. Unlike standard noise suppression, Quail is tuned to improve the performance of downstream Speech-to-Text (STT) engines.
Quail is a general-purpose speech enhancement model.
It works in any setting, single- or multi-speaker and near- or far-field, suppressing background noise while preserving all audible speech. This makes it a good fit whenever every voice should be kept, such as speakerphone setups, meeting rooms, or situations with multiple participants spread across a space.
For primary-speaker isolation, see Quail Voice Focus.