Audio to text, made simple
MorningStar turns speech into editable text with AI. Speaker diarization, timestamps, multilingual support and multiple export formats — built for interviews, meetings, courses and podcasts.
Upload / Record
Upload MP3, WAV, M4A, FLAC and other common audio, or record directly with your microphone and transcribe with one click.
Speaker Diarization
Automatically detects and separates different speakers (Speaker 1 / Speaker 2) and presents them as a conversation.
Timestamps
Every segment has accurate timestamps. Click any segment to jump to that position in the audio for side-by-side proofreading.
Multilingual
Speech recognition for Mandarin and many languages, with one-click translation of the transcript to your target language.
Audio Trimming
Trim irrelevant parts after upload, then transcribe or save to your library to save quota and boost efficiency.
Export & Translate
Export to TXT / SRT / VTT — SRT and VTT work directly as video subtitles. One-click copy and full-text translation included.
Get started in 3 steps
Upload or record
Drag in an audio file, or record voice directly with your microphone.
AI transcribes
Speech recognition with speaker diarization produces a timestamped conversation.
Review, edit & export
Proofread, translate, export TXT/SRT/VTT, or save to your audio library.
Supported audio formats
Great for
Interviews
Separate interviewer and interviewee to build interview transcripts quickly.
Meetings
Turn meeting recordings into text minutes that are easy to search and archive.
Courses & lectures
Convert lectures into notes and jump back to key points with timestamps.