TXT
Plain text
Useful for notes, archives, search, and rewriting.
Audio to text · Video transcription
Turn a recording into text you can actually work with
Upload a meeting, interview, lecture, podcast, or video. Review the timed transcript, then translate it while keeping timestamps and speaker labels, or export it as text or subtitles.
customer-interview.wav
English · 12 minutes · 2 speakers
00:00Speaker 1
00:34Speaker 2
01:12Speaker 1
Choose the result that fits the next job
TIMELINE
Text with timestamps
Jump back to the exact moment without scrubbing through the whole recording.
SRT · VTT
Subtitles and translation
Translate after review, then export a translated or bilingual SRT, or keep the original VTT.
From a media file to editable text
1
Upload audio or video
Choose the source language and turn on speaker recognition for conversations.
2
Transcribe and review
Check names and terms in each timed segment. Long jobs remain available in transcription history.
3
Translate or export
Choose a target language when needed, then download the original text, translation, or bilingual subtitles.
Good reasons to transcribe first
Meetings and interviews
Keep the full conversation before turning it into decisions, notes, and action items.
Lectures and podcasts
Create a searchable record that can later become an article or summary.
Video subtitles
Start with timed captions instead of typing every line by hand.
Accuracy is not one fixed number
Clear speech, limited overlap, and the right source-language setting usually produce a stronger transcript. Dialects, background music, distant microphones, and uncommon names may still need a human pass. Before publishing, listen back to names, numbers, brands, and important claims.
Read the accuracy guideInput and output details
- Input
- MP3, WAV, M4A, AAC, FLAC, MP4, MOV, WebM
- Source language
- Detect automatically or select the main spoken language
- Translation
- Chinese, English, Japanese, Korean, Spanish, French, German, and Portuguese
- Conversations
- Optional speaker recognition is preserved with timestamps in translation
- Output
- Online editing, original or translated TXT and SRT, bilingual SRT, and original VTT
Questions people ask before uploading
Can I transcribe a video?
Yes. Vimorph reads the video's audio track and can return timed text or a subtitle file.
Can it identify speakers in a meeting?
You can enable speaker recognition. Overlapping speech and large differences in microphone distance may still need correction.
Can I translate a finished transcript?
Yes. Review the source transcript first, then choose a target language. Timestamps and speaker labels stay attached to the translated segments.
Does translation replace the original transcript?
No. The source transcript and translation are stored separately, so you can switch between them.
Can I export bilingual subtitles?
Yes. Export translated TXT or SRT alone, or an SRT containing both the source text and translation.
Do I need to keep the page open?
No. Processing continues in the background, and the job can be reopened from transcription history.
Have a recording to sort out?
Upload the original file first. After review, export the source transcript, a translation, or bilingual subtitles.