Soniox releases STT v6 speech-to-text API
Understand this story
Soniox released its speech-to-text API Soniox STT v6, adding two features: agent text input and echo filtering. The model reads what the agent says in order to recognize short replies, and filters out the agent's own speech leaking from the speaker. The new features apply only to the real-time model stt-rt-v6 and are not available in the asynchronous model. The v5 model is deprecated and will be removed on December 15, 2026, after which v5 requests will be automatically routed to v6. Agent text is billed by input text tokens, at a real-time price of $4 per 1 million tokens.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- MarkTechPostSoniox STT v6 Adds Agent Text Input and Echo Filtering for Voice Agents
Soniox released STT v6, a speech-to-text model available as stt-rt-v6 for streaming and stt-async-v6 for files across 60+ languages, which accepts the voice agent's own text to better recognize short caller replies and filter out leaked agent audio. Agent text input is enabled via an "enable_agent_text_input" flag on the real-time model only, with text streamed as JSON frames over the same WebSocket as caller audio. Soniox has published no v6 accuracy or latency numbers; v5 scored 1.34% semantic WER on the Pipecat benchmark, and v5 models are deprecated with removal on December 15, 2026.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 9Nov 4 07:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.