Why streaming transcription drifts to English on multilingual audio — and how to fix language steering

Streaming speech-to-text systems often default to English when processing multilingual audio due to a confidence problem rather than a language deficiency. This drift occurs because streaming models must quickly interpret short audio segments, leading to uncertainty and a fallback to English, which is heavily represented in ASR training data. Factors such as short utterances, code-switching, noise, and accents exacerbate this issue. To address this, it is crucial to select models like Universal-3.5 Pro Realtime that support native code-switching and match the language usage of the target audience. Additionally, providing the model with context, setting language biases when appropriate, and anchoring vocabulary with key terms can improve transcription accuracy. Importantly, forcing a single language on mixed-language audio can backfire, so the strategy should be to steer the model with context rather than restrict it.