Soniox STT Now Available for Telnyx Voice AI

Contact us

Log in

Soniox STT is now available on Telnyx, giving voice AI teams another real-time speech-to-text option for live transcription. Developers can use Soniox for automatic language detection, streaming transcription, and voice agent workflows.

soniox/stt-rt-v4

without a language hint when caller language is not known in advance.You can also configure Soniox STT through the Assistants API by setting transcription.model

to soniox/stt-rt-v4

.

curl -X POST https://api.telnyx.com/v2/ai/assistants \
  -H "Authorization: Bearer $TELNYX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "soniox-stt-assistant",
    "model": "moonshotai/Kimi-K2.5",
    "instructions": "You are a voice assistant for live customer conversations.",
    "transcription": {
      "model": "soniox/stt-rt-v4",
      "language": "auto",
      "settings": {
        "interim_results": true,
        "enable_endpoint_detection": true,
        "max_endpoint_delay_ms": 1000
      }
    }
  }'

Learn more in the Telnyx Speech-to-Text models documentation.