Select language and format
Choose one audio or video source with more than two seconds of audio, then select Chinese, English, or Japanese and SRT, ASS, or TXT.
Speech → Subtitles · iPhone + iPad
Recognize spoken Chinese, English, or Japanese in an audio or video source, review the text, and export SRT, ASS, or TXT. A dedicated Embed in Video action can continue the subtitle result into visible captions.
Recognition first, rendering optional
This tool generates a subtitle document. Burning that text into video is a separate Pro workflow, so you can review the words before changing any frames.
Choose one audio or video source with more than two seconds of audio, then select Chinese, English, or Japanese and SRT, ASS, or TXT.
Allow speech-recognition access, run Apple Speech, and correct names, punctuation, or misunderstood words in the result.
Save the subtitle file, or use the dedicated Embed in Video action to continue into Burn In Subtitles.
SRT and ASS preserve timed cues for caption workflows; TXT is useful when you mainly need readable transcript text. Recognition is only a first draft: background noise, names, accents, and specialist vocabulary can require corrections.
Speech to Subtitles uses Apple Speech and requires system speech-recognition permission. Availability and quality depend on the selected language, device, Apple system services, and current network environment, so it should not be treated as guaranteed offline processing.
Recognize speech, fix the details, and choose whether the subtitles remain separate or become part of a video.