Tag
7 articles
Learn how to interact with Alibaba's Qwen3.5-LiveTranslate-Flash real-time multimodal translation model using WebSocket API. Build a Python application that sends audio input and receives translated speech output.
OpenAI has launched three new realtime audio models—GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper—enhancing real-time voice interaction capabilities for developers.
IBM has launched two new Granite Speech 4.1 2B models — one autoregressive for high-accuracy speech recognition with translation, and one non-autoregressive for fast inference.
Learn how to use Tencent's 440 MB AI translation model to perform offline translations in 33 languages using Python.
DeepL has launched real-time voice-to-voice translation in over 40 languages, aiming to enhance global communication for meetings, group conversations, and enterprise use.
Google is launching Live Translate with Headphones on iOS, enabling real-time translation through headphones. The feature expands translation capabilities to more countries and devices.
RWS has launched Language Weaver Pro, a new translation model that ranks first in 31 of 32 languages according to internal benchmarks. The tool is now natively integrated into the Trados portfolio.