DeepL's Aure model carries speaker tone into real-time translation
Aure runs in DeepL Voice meetings, in-person mode, and the API across eight languages, replacing a static voice sample.
Stories per day · 30 days
4 stories, newest first · one card per story
Stories tagged #speech-translation
DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMs
DirectSpeech2LLM cuts speech-LLM prompt overfitting, generalizing from ASR-only training to translation and emotion tasks.
Alibaba Qwen Team Releases Qwen3.8-LiveTranslate: A Real-Time Interpretation Model That Cuts Average Lag to 2.3 Seconds Across 60 Languages
Alibaba's Qwen team launched Qwen3.8-LiveTranslate, a real-time speech translation model cutting average lag from 2.8 to 2.3 seconds across 60 languages.
3
Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning
Kraken speech-to-speech translation model builds on Qwen3-8B with low-bitrate vector quantization and source-conditioned vocoding.