Veterinary Mode (beta)

Veterinary Mode is an add-on that enhances streaming transcription accuracy for veterinary terminology, such as animal medication names, procedures, and conditions. Use it for veterinary use cases where general-purpose transcription frequently gets these terms wrong. Veterinary Mode can be used with all of our Real-time STT models. Enable Veterinary Mode by setting the domain connection parameter to "veterinary-v1". No other changes to your existing pipeline are required.

Quickstart

Set domain to "veterinary-v1" as a connection parameter when you open the WebSocket.

Python
Python SDK
Javascript
JavaScript SDK

CONNECTION_PARAMS = {
    "sample_rate": 16000,
    "speech_model": "universal-3-6-pro",
    "domain": "veterinary-v1",
}

client.connect(
    RealTimeParameters(
        sample_rate=16000,
        speech_model="universal-3-6-pro",
        domain="veterinary-v1",
    )
)

const CONNECTION_PARAMS = {
  sample_rate: 16000,
  speech_model: "universal-3-6-pro",
  domain: "veterinary-v1",
};

const transcriber = client.streaming.transcriber({
  sampleRate: 16_000,
  speechModel: "universal-3-6-pro",
  domain: "veterinary-v1",
});

Use cases

Veterinary Mode is designed for veterinary AI applications where accurate clinical terminology is critical:

Real-time veterinary scribes: Deliver accurate transcripts to veterinarians during or immediately after an exam.
Front-office voice agents: Handle drug names and clinic-specific terminology in scheduling calls and client follow-ups.
Veterinary contact centers: Transcribe calls with correct veterinary vocabulary for downstream processing and quality assurance.

Combine with other features

Veterinary Mode works alongside other streaming features. You can combine it with:

Streaming Diarization to separate the veterinarian from the pet owner
Keyterms Prompting to further boost accuracy for specific terms unique to your practice

Python
Python SDK
Javascript
JavaScript SDK

CONNECTION_PARAMS = {
    "sample_rate": 16000,
    "speech_model": "universal-3-6-pro",
    "domain": "veterinary-v1",
    "speaker_labels": "true",
    "keyterms_prompt": json.dumps(["Apoquel", "Bravecto", "Cytopoint"])
}

client.connect(
    RealTimeParameters(
        sample_rate=16000,
        speech_model="universal-3-6-pro",
        domain="veterinary-v1",
        speaker_labels=True,
        keyterms_prompt=["Apoquel", "Bravecto", "Cytopoint"],
    )
)

const CONNECTION_PARAMS = {
  sample_rate: 16000,
  speech_model: "universal-3-6-pro",
  domain: "veterinary-v1",
  speaker_labels: true,
  keyterms_prompt: JSON.stringify(["Apoquel", "Bravecto", "Cytopoint"]),
};

const transcriber = client.streaming.transcriber({
  sampleRate: 16_000,
  speechModel: "universal-3-6-pro",
  domain: "veterinary-v1",
  speakerLabels: true,
  keytermsPrompt: ["Apoquel", "Bravecto", "Cytopoint"],
});

Getting started

Features

API reference

Advanced

Integrations

Guides

Veterinary Mode (beta)

Quickstart

Use cases

Combine with other features

​Quickstart

​Use cases

​Combine with other features

Quickstart

Use cases

Combine with other features