customers
All customer stories
Top Voice AI companies are building with Assembly.
resources
Latest Release
Universal 3.5 Pro
Our new flagship speech-to-text model handles real-world audio the way it actually happens. Available for real-time and pre-recorded audio.
resources
Clinical research depends on accurate records — interviews, trial visits, adverse-event reports, all dense with medical terminology. Universal-3.5 Pro with Medical Mode delivers a 3.2% Missed Entity Rate plus entity detection and PHI redaction, so your analysis starts from data you can trust.
Missed Entity Rate on clinical conversations with Medical Mode.
Fewer missed medical entities than Universal-3 Pro alone.
Fewer medical entity errors than the base model.
Lowest Missed Entity Rate vs. Deepgram, Speechmatics, AWS, and Google.
One request returns the transcript plus detected entities — structured data ready for coding and analysis.
import assemblyai as aai
aai.settings.api_key = "YOUR_API_KEY"
# Clinical research: interviews, adverse events, trial terms
config = aai.TranscriptionConfig(
speech_models=["universal-3-5-pro", "universal-2"],
domain="medical-v1",
entity_detection=True,
keyterms_prompt=["adverse event", "placebo", "randomized", "informed consent"],
)
transcript = aai.Transcriber().transcribe("./study-interview.wav", config)
print(transcript.text)Drug names, conditions, and protocol terms captured across long interviews.
Entity detection and topic detection turn transcripts into analyzable data.
PHI redaction, BAA available, EU data residency for international studies.
Trusted by the world’s leading enterprises
