Gradium Launches stt-translate and s2s-translate, Real-Time Speech Translation Models Beating gpt-realtime-translate on Accuracy and Latency

Gradium launched two real-time speech translation models, stt-translate and s2s-translate, covering 20 language pairs across English, French, German, Spanish, and Portuguese. The models collapse the standard three-model cascade into two, achieving better accuracy and latency than gpt-realtime-translate and gemini-3.5-live-translate, with added voice selection and cloning.

Gradium released two real-time speech translation models, stt-translate and s2s-translate, covering English, French, German, Spanish, and Portuguese across 20 language pairs. The models collapse the standard three-model cascade into two, pairing single-pass transcription-and-translation with a Gradium TTS stage over one duplex WebSocket. Gradium reports a better accuracy-latency tradeoff than gpt-realtime-translate and gemini-3.5-live-translate, plus output voice selection and cloning. The post Gradium Launches stt-translate and s2s-translate, Real-Time Speech Translation Models Beating gpt-realtime-translate on Accuracy and Latency https://www.marktechpost.com/2026/06/24/gradium-launches-stt-translate-and-s2s-translate-real-time-speech-translation-models-beating-gpt-realtime-translate-on-accuracy-and-latency/ appeared first on MarkTechPost https://www.marktechpost.com .