What is the best veterinary transcription API?

Veterinary documentation needs the same entity accuracy as human medicine — drug names, dosages, conditions. Universal-3.5 Pro with Medical Mode reaches a 3.2% Missed Entity Rate and handles veterinary vocabulary with one parameter.

Does Medical Mode work for animal patients?

Yes. Medical Mode targets clinical vocabulary — medications, dosages, conditions, procedures — which applies directly to veterinary care. Add species and drug terms via keyterms for a further boost.

Can it run live in the veterinary exam room?

Yes, on Universal-3.5 Pro Realtime at ~150ms P50 latency, including handheld and far-field audio.

How do I improve accuracy on specific drugs or breeds?

Pass them in keyterms_prompt (up to 1,000 terms async, 100 realtime) — e.g., meloxicam, brachycephalic, FeLV.

How much does veterinary transcription with Medical Mode cost?

$0.15/hr on top of Universal-3.5 Pro — pay-as-you-go, no commitments.

How do I get started with veterinary transcription?

Add domain: "medical-v1" to your request and run your own audio in the playground.

Veterinary

A medical scribe that knows species, breeds, and vet drug names

Veterinary medicine has its own vocabulary — meloxicam dosed by weight, brachycephalic, FeLV, equine vs. feline. The same Medical Mode that captures human clinical terms handles veterinary terminology, so your scribe drafts an accurate record whether the patient walks in on two legs or four. Works for doctors, works for you.

Try it free on your audio Read the docs

The lowest Missed Entity Rate across benchmarked providers — applied to veterinary vocabulary

Missed Entity Rate 3.2%

Missed Entity Rate on clinical conversations with Medical Mode.

vs. Universal-3 Pro ~20%

Fewer missed medical entities than Universal-3 Pro alone.

vs. base model 87%

Fewer medical entity errors than the base model.

Benchmarked providers #1

Lowest Missed Entity Rate vs. Deepgram, Speechmatics, AWS, and Google.

See the medical benchmarks

Activation

One parameter — built on the same medical model

No model swap, no re-integration — the same one-line Medical Mode change, tuned to veterinary vocabulary, on async or realtime.

import assemblyai as aai

aai.settings.api_key = "YOUR_API_KEY"

# Veterinary: species, breeds, vet drugs and dosages
config = aai.TranscriptionConfig(
    speech_models=["universal-3-5-pro", "universal-2"],
    domain="medical-v1",
    keyterms_prompt=["meloxicam", "brachycephalic", "FeLV", "feline", "0.1 mg/kg"],
)

transcript = aai.Transcriber().transcribe("./vet-consult.wav", config)
print(transcript.text)

Vet drug names and dosages

Weight-based dosing and species-specific medications land accurately.

Universal-3.5 Pro

Species & breed terminology

From brachycephalic breeds to equine conditions.

Medical Mode

Exam-room or mobile

Async for recorded consults, realtime for live in-room documentation; robust on far-field and handheld audio.

Universal-3.5 Pro Realtime

Common questions

: Veterinary documentation needs the same entity accuracy as human medicine — drug names, dosages, conditions. Universal-3.5 Pro with Medical Mode reaches a 3.2% Missed Entity Rate and handles veterinary vocabulary with one parameter.
: Yes. Medical Mode targets clinical vocabulary — medications, dosages, conditions, procedures — which applies directly to veterinary care. Add species and drug terms via keyterms for a further boost.
: Yes, on Universal-3.5 Pro Realtime at ~150ms P50 latency, including handheld and far-field audio.
: Pass them in keyterms_prompt (up to 1,000 terms async, 100 realtime) — e.g., meloxicam, brachycephalic, FeLV.
: $0.15/hr on top of Universal-3.5 Pro — pay-as-you-go, no commitments.
: Add domain: "medical-v1" to your request and run your own audio in the playground.

Try it free on your audio

Run your own consult audio through Medical Mode in the playground — one parameter, no model swap. Free to start, no credit card required.

Try it free