{"type":"ScholarlyArticle","title":"DeepL Voice: Real-Time Speech-to-Speech Translation","authors":[{"name":"Johannes Ernesti","slug":"johannes-ernesti","given":"Johannes","family":"Ernesti","affiliation":""},{"name":"Peter Kaiser","slug":"peter-kaiser","given":"Peter","family":"Kaiser","affiliation":""},{"name":"Jonas Heinze","slug":"jonas-heinze","given":"Jonas","family":"Heinze","affiliation":""},{"name":"Elnaz Shafaei-Bajestan","slug":"elnaz-shafaei-bajestan","given":"Elnaz","family":"Shafaei-Bajestan","affiliation":""},{"name":"Kristina Geißler","slug":"kristina-gei-ler","given":"Kristina","family":"Geißler","affiliation":""},{"name":"Weiyue Wang","slug":"weiyue-wang","given":"Weiyue","family":"Wang","affiliation":""},{"name":"Johannes Beck","slug":"johannes-beck","given":"Johannes","family":"Beck","affiliation":""},{"name":"Sascha Brinker","slug":"sascha-brinker","given":"Sascha","family":"Brinker","affiliation":""},{"name":"Thorben Finke","slug":"thorben-finke","given":"Thorben","family":"Finke","affiliation":""}],"abstract":"DeepL Voice is a real-time speech-to-speech translation system for global business communication, following a pragmatic incremental approach: developing a production-grade cascaded speech-to-speech-translation (S2ST) system, while exploring end-to-end solutions in parallel.\r\nThe production system (launched November 2024) achieves competitive transcription quality through proprietary real-time ASR models and eliminates translation \"flickering\" via stable text streaming while maintaining low latency.\r\nSupporting 18 input languages and 30+ target languages, it offers DeepL Voice for Meetings (Microsoft Teams/Zoom integration), DeepL Voice for Conversations (mobile apps), as well as the DeepL API for Voice.\r\nKey features include customizable formality and glossary support for business-appropriate communication, with voice cloning TTS under development.","doi":"10.24963/ijcai.2026/962","url":"https://ijcai.org/proceedings/2026/962","pdf":"https://ijcai.org/proceedings/2026/0962.pdf","markdown":"https://ijcai.org/proceedings/2026/962.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/962","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Demo Track","track":"Demo Track","number":962,"pages":{"first":8385,"last":8388},"keywords":["AI: Natural Language Processing","AI: Humans and AI"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}