Audio Language Model5 min read
Soniox STT v6 Adds Agent Text Input and Echo Filtering for Voice Agents
Soniox has released Soniox STT v6, the latest generation of its speech-to-text API. Soniox STT v6 is a speech-to-text model that reads what a voice agent says while hearing the caller. It uses that text to recognize short replies and to drop the agent’s own voice.
By Michal SutterMarkTechPost

Read the full story
Originally published by MarkTechPost on Nov 3, 2026.
Comments
Sign in to join the discussion.