DeepL Voice: Real-Time Speech-to-Speech Translation

Ernesti, Johannes; Kaiser, Peter; Heinze, Jonas; Shafaei-Bajestan, Elnaz; Geißler, Kristina; Wang, Weiyue; Beck, Johannes; Brinker, Sascha; Finke, Thorben

doi:10.24963/ijcai.2026/962

DeepL Voice: Real-Time Speech-to-Speech Translation

Johannes Ernesti, Peter Kaiser, Jonas Heinze, Elnaz Shafaei-Bajestan, Kristina Geißler, Weiyue Wang, Johannes Beck, Sascha Brinker, Thorben Finke

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Demo Track. Pages 8385-8388.

https://doi.org/10.24963/ijcai.2026/962

Keywords

AI: Natural Language Processing
AI: Humans and AI

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.

The 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.

Supporting 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.

Key features include customizable formality and glossary support for business-appropriate communication, with voice cloning TTS under development.

Johannes Ernesti, Peter Kaiser, Jonas Heinze, Elnaz Shafaei-Bajestan, Kristina Geißler, Weiyue Wang, Johannes Beck, Sascha Brinker, and Thorben Finke. 2026. DeepL Voice: Real-Time Speech-to-Speech Translation. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8385–8388. https://doi.org/10.24963/ijcai.2026/962

@inproceedings{ijcai2026p962,
  title     = {DeepL Voice: Real-Time Speech-to-Speech Translation},
  author    = {Ernesti, Johannes and Kaiser, Peter and Heinze, Jonas and Shafaei-Bajestan, Elnaz and Geißler, Kristina and Wang, Weiyue and Beck, Johannes and Brinker, Sascha and Finke, Thorben},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {8385--8388},
  year      = {2026},
  month     = {8},
  note      = {Demo Track},
  doi       = {10.24963/ijcai.2026/962},
  url       = {https://doi.org/10.24963/ijcai.2026/962},
}

TY  - CPAPER
TI  - DeepL Voice: Real-Time Speech-to-Speech Translation
AU  - Ernesti, Johannes
AU  - Kaiser, Peter
AU  - Heinze, Jonas
AU  - Shafaei-Bajestan, Elnaz
AU  - Geißler, Kristina
AU  - Wang, Weiyue
AU  - Beck, Johannes
AU  - Brinker, Sascha
AU  - Finke, Thorben
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 8385
EP  - 8388
DO  - 10.24963/ijcai.2026/962
UR  - https://doi.org/10.24963/ijcai.2026/962
ER  -