Veterinary Mode (beta)

Veterinary Mode is an add-on that enhances 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. Enable Veterinary Mode by setting the domain parameter to "veterinary-v1". No changes to your existing pipeline are required.

Quickstart

Python
Python SDK
JavaScript
JavaScript SDK

To enable Veterinary Mode, set domain to "veterinary-v1" in the POST request body:

import requests
import time

base_url = "https://api.assemblyai.com"
headers = {"authorization": "<YOUR_API_KEY>"}

data = {
    "audio_url": "<YOUR_AUDIO_URL>",
    "language_detection": True,
    "domain": "veterinary-v1"
}

response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)

if response.status_code != 200:
    print(f"Error: {response.status_code}, Response: {response.text}")
    response.raise_for_status()

transcript_response = response.json()
transcript_id = transcript_response["id"]
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"

while True:
    transcript = requests.get(polling_endpoint, headers=headers).json()
    if transcript["status"] == "completed":
        print(transcript["text"])
        break
    elif transcript["status"] == "error":
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
    else:
        time.sleep(3)

To enable Veterinary Mode, set domain to "veterinary-v1" in the transcription config.

from assemblyai.prerecorded.v2 import Transcriber, TranscriptionConfig

# You can use a local filepath:
# audio_file = "./example.mp3"

# Or use a publicly-accessible URL:
audio_file = "<YOUR_AUDIO_URL>"

config = TranscriptionConfig(
    language_detection=True,
    domain="veterinary-v1",
)

transcriber = Transcriber(api_key="<YOUR_API_KEY>")
transcript = transcriber.transcribe(audio_file, config)

print(transcript.text)

To enable Veterinary Mode, set domain to "veterinary-v1" in the POST request body:

const baseUrl = "https://api.assemblyai.com";
const headers = {
  authorization: "<YOUR_API_KEY>",
};

const data = {
  audio_url: "<YOUR_AUDIO_URL>",
  language_detection: true,
  domain: "veterinary-v1",
};

const url = `${baseUrl}/v2/transcript`;
let res = await fetch(url, {
  method: "POST",
  headers: { ...headers, "Content-Type": "application/json" },
  body: JSON.stringify(data),
});
if (!res.ok) throw new Error(`Error: ${res.status}`);
const response = await res.json();

const transcriptId = response.id;
const pollingEndpoint = `${baseUrl}/v2/transcript/${transcriptId}`;

while (true) {
  res = await fetch(pollingEndpoint, { headers });
  if (!res.ok) throw new Error(`Error: ${res.status}`);
  const transcriptionResult = await res.json();

  if (transcriptionResult.status === "completed") {
    console.log(transcriptionResult.text);
    break;
  } else if (transcriptionResult.status === "error") {
    throw new Error(`Transcription failed: ${transcriptionResult.error}`);
  } else {
    await new Promise((resolve) => setTimeout(resolve, 3000));
  }
}

To enable Veterinary Mode, set domain to "veterinary-v1" in the transcription config.

import { AssemblyAI } from "assemblyai";

const client = new AssemblyAI({
  apiKey: "<YOUR_API_KEY>",
});

// You can use a local filepath:
// const audioFile = "./example.mp3"

// Or use a publicly-accessible URL:
const audioFile = "<YOUR_AUDIO_URL>";

const params = {
  audio: audioFile,
  language_detection: true,
  domain: "veterinary-v1",
};

const run = async () => {
  const transcript = await client.transcripts.transcribe(params);
  console.log(transcript.text);
};

run();

Use cases

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

Veterinary scribing: Capture medication names and clinical terms correctly when documenting exams and consultations.
AI-powered clinical notes: Generate clean transcripts for downstream LLMs producing SOAP notes, discharge instructions, and referral letters.
Front-office automation: Handle drug names and clinic-specific terminology in scheduling calls, client follow-ups, and voice agents.
Multi-speaker consultations: Combine with Speaker Diarization to separate the veterinarian from the pet owner.

Combine with other features

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

Speaker Diarization to identify who said what in consultations
Keyterms Prompting to further boost accuracy for specific terms unique to your practice

Python
Python SDK
JavaScript
JavaScript SDK

data = {
    "audio_url": "<YOUR_AUDIO_URL>",
    "language_detection": True,
    "domain": "veterinary-v1",
    "speaker_labels": True,
    "keyterms_prompt": ["Apoquel", "Bravecto", "Cytopoint"]
}

config = TranscriptionConfig(
    language_detection=True,
    domain="veterinary-v1",
    speaker_labels=True,
    keyterms_prompt=["Apoquel", "Bravecto", "Cytopoint"],
)

const data = {
  audio_url: "<YOUR_AUDIO_URL>",
  language_detection: true,
  domain: "veterinary-v1",
  speaker_labels: true,
  keyterms_prompt: ["Apoquel", "Bravecto", "Cytopoint"],
};

const params = {
  audio: audioFile,
  language_detection: true,
  domain: "veterinary-v1",
  speaker_labels: true,
  keyterms_prompt: ["Apoquel", "Bravecto", "Cytopoint"],
};

Getting started

Features

API reference

Advanced

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