ASR · TTS · VOICE CLONE · DUBBING
Explore capabilitiesReal-time transcription for Chinese, English, and Thai as people speak. Multi-speaker meetings are automatically separated by speaker and turned into structured notes.
Even when speakers mix languages mid-sentence, every word is transcribed in its original script—and full videos get bilingual subtitles.
Dub videos into a new language with matching lip movements, or integrate file transcription, streaming ASR, and text-to-speech into your product via API in a few lines of code.
FROM THE BLOG
Thai has no spaces between words, so WER shifts with the tokenizer. Why we use character error rate as the main metric, and how we normalize text first.
From recording and speaker separation to the summary and action items: how a 40-minute Thai meeting becomes a set of minutes.
Where models go wrong when Thai speech contains English brand names and Chinese personal names, and how to score the results.