Speech Recognition and Audio Understanding

Play the entire pageVoiced by BosonAI

Transform spoken language, audio and music into precise, context-aware text that accurately captures speakers, emotions and understands intent.

Loading content...

Advanced voice synthesis for natural and expressive audio, including multi-speaker promptable dialog, and voice cloning. Now open source.

Advanced techniques for training large language models and finetuning for specific applications.

Comprehensive data collection, annotation and processing pipelines for high-quality model training, fine-tuning and alignment.