Introducing Soniox STT v6

Soniox@soniox_aiNov 3, 2026

Introducing Soniox STT v6, the world’s first speech recognition model that knows what your voice agent is saying and automatically filters out the agent’s own voice. Two connected innovations make this possible: → Agent text input gives recognition context from both sides of https://t.co/ke1FcOIsiE

Views488.2k
Comments103
Reposts41
Likes511
Launched Nov 3, 2026View post

More from Soniox

1

Soniox TTS v2 major voice-clone improvement

@soniox_ai

We’ve shipped a major improvement to voice cloning in Soniox TTS v2. You can now create an instant voice clone from up to 2 minutes of reference audio, compared with 20 seconds before. The longer sample gives the model much more information about the voice, including phonemes, https://t.co/E5bkIQXDgL

Sep 4, 2026
Views119.6k
Comments4
Reposts5
View post

See all Soniox launches →