AI · Official
ElevenLabs Launches Scribe v3 Live Medical to Improve Medical Accuracy in Voice Agents
ElevenLabs blog ·

At a glance
ElevenLabs has released Scribe v3 Live Medical, a speech-to-text model for live phone calls that is tuned for medical language. It aims to stop voice agents from mishearing drug names and other clinical details during calls.
Key points
- A voice agent can mishear drug names; in one test, sitagliptin was transcribed as citalopram, a different antidepressant.
- The model is built on Scribe v3 Live and is available now in ElevenAgents.
- Healthcare teams can add up to 10,000 custom terms, which the model uses only when a caller seems to say one of them.
- In ElevenLabs' tests, it made fewer errors than other medical models, and up to 48% fewer errors on medical terms with a custom term list loaded.
Why it matters
Voice agents in healthcare can record wrong medication details, which could affect patient care. Better live transcription makes these calls more reliable.
Original source
Scribe v3 Live Medical helps conversational agents get clinical details right
ElevenLabs blog · Nov 17, 21:00 KST
Read on ElevenLabs blog ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to ElevenLabs blog.
More from this field
- Designers Say Ssense's Website Shows Their Clothes Inaccurately
Designer Reese Cooper noticed his RCOS puffer coat looked distorted on the luxury retailer Ssense's website, with a chest hook drawn far too large. Ssense said some site images came from a "virtual try-on" program, though it would not say whether that program uses AI.
The New York Times · Nov 21, 06:16 KST - Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST - Leaky AI Supply Chain Exposes Secret User Data at Alarming Rate
A research test sent nearly two million prompts with fake but working secrets through a network of AI services to see where they ended up. Many of the secrets were stolen, and attackers used them to reach cloud accounts. The results point to weak protection of customer data along the chain.
Ars Technica · Nov 21, 05:59 KST