Medical Speech-to-Text Now Available for Telnyx Voice AI

Omi Health's medical speech-to-text model omi-health/omi-med-stt-v1 is now available as a Telnyx STT engine, Telnyx announced, bringing self-hosted, medical-tuned transcription to voice AI workflows. The model, a fine-tune of nvidia/parakeet-tdt-0.6b-v2 that runs on the same self-hosted Parakeet stack as nvidia/parakeet-v3, targets clinical dialogue, medication names and dosages, and is reachable via transcription_start, TeXML <Gather> or <Transcription>, WebSocket streaming, AI Assistants transcription settings, or the OpenAI SDK-compatible Speech-to-Text REST API. On streaming surfaces it accepts linear16 or linear32 audio at 16 kHz and returns final transcripts only, with no interim or partial results and endpointing ignored; the REST endpoint transcribes synchronously, forces mono, and caps uploads at 100 MB.

Contact us https://telnyx.com/contact-us Log in https://portal.telnyx.com Omi Health's medical speech-to-text model, omi-health/omi-med-stt-v1 , is now available as a Telnyx STT engine, bringing self-hosted, medical-tuned transcription to voice AI workflows. Built as a fine-tune of nvidia/parakeet-tdt-0.6b-v2 , the model targets clinical dialogue, medication names, and dosages, and runs on the same self-hosted Parakeet stack as nvidia/parakeet-v3 . omi-health/omi-med-stt-v1 is trained on clinical dialogue and transcribes medication names, dosages, and medical terminology more accurately than general-purpose models. transcription start , TeXML <Gather or <Transcription , WebSocket streaming, AI Assistants transcription settings, or the Speech-to-Text REST API for file transcription. linear16 or linear32 audio at 16 kHz. For Call Control, POST to transcription start : { "transcription engine": "Parakeet", "transcription engine config": { "transcription engine": "Parakeet", "transcription model": "omi-health/omi-med-stt-v1" } } For TeXML <Gather : <Gather transcriptionEngine="Parakeet" model="omi-health/omi-med-stt-v1" <Say Please describe your symptoms after the tone.</Say </Gather For WebSocket streaming: wss://api.telnyx.com/v2/speech-to-text/transcription?transcription engine=Parakeet&model=omi-health/omi-med-stt-v1&input format=linear16&sample rate=16000 On streaming surfaces, omi-health/omi-med-stt-v1 accepts linear16 or linear32 audio at 16 kHz and returns final transcripts only. No interim or partial results. Endpointing is ignored. For file transcription, POST to the Speech-to-Text REST API. It's OpenAI SDK compatible, so swapping base url and api key is enough for existing Whisper-style code: python from openai import OpenAI client = OpenAI api key="YOUR TELNYX API KEY", base url="https://api.telnyx.com/v2", result = client.audio.transcriptions.create model="omi-health/omi-med-stt-v1", file=open "visit-recording.mp3", "rb" , The REST endpoint transcribes synchronously, forces mono, and caps uploads at 100 MB. Learn more in the Speech-to-Text models docs https://developers.telnyx.com/docs/voice/stt/models , the Speech-to-Text REST API overview https://developers.telnyx.com/docs/voice/stt/rest-api , or the AI Assistants transcription settings https://developers.telnyx.com/docs/inference/ai-assistants/transcription-settings .