The Retell Community is where innovators, call center leaders, and AI enthusiasts come together to share ideas, learn best practices, and explore the future of voice automation. Join to connect with peers, get early access to product updates, and collaborate on building human-like AI voice experiences that transform customer service.

Retell AI

<@605090813025976344> Can you guys share which concrete speech-to-text models are currently used for AssemblyAI, Soniox, Azure and Deepgram? This will make our choice a bit more informed.

Also, is Retell relying on the STT provider endpointing to make the turn-taking decision or you guys do this on your own? (again, may impact our choice of STT provider)