-

Krisp Launches Voice Translation v3, Opens Enterprise-Grade Translation to Developers

The same engine that powers live healthcare and high-stakes contact center calls is now self-serve via API, with new quality controls for enterprise.

BERKELEY, Calif.--(BUSINESS WIRE)--Krisp, the leader in real-time voice AI technology, today announced Voice Translation v3, a major release for its enterprise voice translation solution, and the launch of the Voice Translation API. The same engine that delivered 96% accuracy in a live healthcare deployment is now available to developers via self-serve API.

The same engine that delivered 96% accuracy in a live healthcare deployment is now available to developers via self-serve API.

Share

For enterprises and BPOs running translated calls at scale, accurate translation has never been the only challenge. Operations leaders need to know whether translation is working on every call, not just a sample. Quality teams need proof that names, numbers, and regulated content survived the translation. Developers building voice products outside the contact center have faced a similar wall. Their users speak multiple languages, but most translation tools fall apart on noisy audio, accented speech, and domain-specific terms. Voice Translation v3 closes both gaps.

For contact centers and BPOs, Voice Translation v3 adds the controls and visibility that make multilingual operations measurable.

"Real-time voice translation is having its moment, but most of what is shipping was built on general data and not tested where accuracy matters," said Davit Baghdasaryan, CEO and Co-Founder of Krisp. "We built our engine for the most difficult environments: live calls in healthcare, insurance, and financial services where one wrong word has real consequences. That is what moves translation from a feature to an operational infrastructure. Today that engine is available to enterprises as a managed product and to developers as a self-serve API. ”

What’s New: Operational Control for the Enterprise

Voice Translation v3 adds the controls and visibility that make multilingual operations measurable:

  • Accuracy QA: Automatically scores the accuracy of 100% of translated calls across four quality dimensions.
  • Quick Phrases: Pre-written, regulated content delivered as translated speech in any language.
  • Live Call Audit: Admins can listen to the call from the customer’s and agent’s perspective and access a live bi-lingual transcript in real time.
  • Language Auto-Selection: Right language at call start, no manual setup.
  • Custom Vocabulary and Dictionary: Customize how the engine recognizes and translates industry terms.
  • 61 languages in any pair: Including US Spanish, French Canadian, Egyptian Arabic, and more regional variants.

For developers, the Voice Translation API ships with the same engine, the same accuracy, and the same 61 languages.

The same engine, now self-serve for developers:

  • Same engine, self-serve: Sign up, get a key, ship. No sales call.
  • One WebSocket: Speech in, translated speech and text out.
  • SDKs: JavaScript and Python at launch, C++ coming soon.
  • Domain control from day one: Custom Vocabulary and Dictionary built in.
  • 99.9% uptime SLA: Same as the enterprise product.
  • 60 free minutes: Test before scaling.

"Developers building telehealth, customer support, fintech, and other accuracy-critical products need more than a demo that works on clean audio," said Robert Schoenfield, EVP of Licensing and Partnerships at Krisp. "They need an engine that has already been tested in live, high-stakes calls. The Voice Translation API gives them direct access to that engine, with a developer experience that does not require a sales call to get started."

Voice Translation v3 builds on production results from live deployments. In a live healthcare deployment, the engine completed 90% of multilingual calls end-to-end with no human interpreter, achieved 96% overall translation accuracy, and recorded zero patient safety or experience incidents across 8+ languages. In benchmark testing across 30 languages and 6 business domains, AutoQA scores landed consistently between 93 and 97, with results independently confirmed by bilingual linguist reviewers.

Voice Translation v3 is available now to enterprise contact center and BPO customers. The Voice Translation API is available today through the Krisp developer dashboard, with 60 minutes of free translation credit and self-serve subscription pricing.

About Krisp

Founded in 2017, Krisp builds real-time Voice AI for meetings, contact centers, and developers. Its Voice AI technology enhances digital voice communication through bidirectional accent conversion, live speech-to-speech translation in over 60 languages, agent assist, and speech analytics–all built on patented, award-winning noise cancellation models. Krisp applications are privacy-first, using industry-standard security practices across all audio hardware configurations and applications that support digital voice communication. Today, Krisp is deployed on over 200 million devices and processes over 80 billion minutes of voice conversations every month, with innovations recognized by Forbes, TIME, Gartner, and Fast Company, and won two 2026 Webby Awards for Technical Achievement.

Learn more about Krisp Voice Translation

Contacts

Media Contact
Shara Maurer
smaurer@krisp.ai

Krisp


Release Versions

Contacts

Media Contact
Shara Maurer
smaurer@krisp.ai

Social Media Profiles
More News From Krisp

Krisp Names Graham Brown Chief Growth Officer for Europe and Africa

BERKELEY, Calif. & LONDON--(BUSINESS WIRE)--Krisp, the leader in real-time Voice AI, today announced the appointment of Graham Brown as Chief Growth Officer, Europe and Africa. Brown will lead Krisp's commercial strategy across the UK, Europe and Africa, reporting to Chief Commercial Officer Harry Folloder. Brown joins Krisp from Capita and brings nearly 30 years of contact centre experience to the role, including 25 years in CX outsourcing. He has held senior leadership positions at Alorica, H...

Krisp Launches VIVA 2.0, Introducing Voice Infrastructure for Voice AI Agents

BERKELEY, Calif.--(BUSINESS WIRE)--Krisp today launched Krisp VIVA 2.0, the voice AI infrastructure layer for voice agents, IVRs, and conversational AI. The release introduces a new generation of small, real-time models that improve WER, predict when users finish speaking, classify interruptions, and read perceptual signals like synthetic speech, gender, and accent, setting a new benchmark for how voice agents handle audio in production. Voice agent usage grew 9x in 2025, yet most voice agents...

Krisp Launches Accent Conversion with British English Output

BERKELEY, Calif.--(BUSINESS WIRE)--Krisp, the pioneer in real-time voice AI technology, today announced British English output for its AI-powered Accent Conversion technology. Agents based in India, the Philippines, Africa, the Middle East, the U.S., and Pakistan can now convert their voice to natural British English in real time. The technology works on-device, with no enrollment required and no changes to existing workflows. Accent Conversion transforms an agent’s natural speech to British En...
Back to Newsroom