AI DubbingStudioAudio to SRT converts uploaded speech into a source-language transcript and separate SRT, VTT and TXT files. It detects the spoken language automatically and accepts files up to 10 minutes and 200 MiB.
This audio recording transcription tool recognizes speech in its original language. Upload a file, review its duration quote, and download SRT, VTT or TXT. It does not translate the transcript or create a voice track.
Upload MP3, WAV or M4A up to 200 MiB and 10 minutes. Transcription costs 1 credit per started 30 seconds, with a minimum of 1 credit; review the duration quote before running. There is no free transcription preview.
| Format | Contents |
|---|---|
| SRT | Numbered segments with start and end timestamps |
| VTT | Timed segments with a WebVTT header |
| TXT | Recognized words without timestamps |
Segment normalization can merge or omit very short tail fragments. Check names, numbers and timings against your recording, especially for noisy or overlapping speech. The workspace has no transcript editor or speaker reassignment; correct downloaded files in your editor.
Upload only recordings you own or have permission to use. Transcription recognizes speech; it does not extract on-screen text, translate the transcript or generate a voice. See pricing and the terms.
Upload your authorized audio recording. The server checks its duration before transcription; speech recognition then detects the spoken language automatically. Text visible in video frames is not extracted.
Read the timestamped segments beside your source. Check names, numbers and overlapping speech against the recording. Correct the downloaded transcript in your own editor; the workspace has no transcript editor.
Download SRT or VTT for captions, or TXT for reading and editing. These are separate files; transcription does not burn captions into video or generate translated speech.
Podcast producers
Create a source-language transcript from your audio recording for notes and reuse. Review automatic recognition before publishing.
Course instructors
Prepare a readable companion to a recorded lesson. Check specialist vocabulary and names against the source.
Interview researchers
Use timestamped segments to revisit an interview. Verify quotations and speaker context yourself.
Narration editors
Take SRT or VTT into your caption workflow. Adjust wording and timings in your preferred editor.
Choose your audio recording and sign in. The server probes its duration without transcribing it.
Review the duration-based credit quote, then explicitly start transcription. There is no free transcription preview.
Check the source-language transcript against the recording. Download TXT, SRT or VTT and correct it in your editor.
Translate MP3, WAV or M4A into AI speech in 13 languages. Try a free 30-second preview, then download audio and SRT/VTT subtitles online.
Translate a video into 13 languages with AI dubbing. Try a free 30-second voice preview, then download video, audio and separate SRT/VTT subtitles.
Translate UTF-8 SRT or VTT files up to 2 MiB into 1–5 languages. Download both formats with original timings, from 1 credit per minute per language.
AI lip sync for one front-facing speaker in videos up to 210 seconds. Preview the translated voice free for 30 seconds before full dubbing.
Bring a file you have permission to use. Review the quote before starting a paid run.
Upload the file, check its duration and credit quote, then run transcription. Review the timestamped text and download SRT, VTT or TXT.
MP3, WAV or M4A files up to 10 minutes and 200 MiB per upload are supported. Longer files must be shortened before uploading.
1 credit per started 30 seconds, with a minimum of 1 credit. A 30-second file costs 1 credit; 31 seconds costs 2; 10 minutes costs 20. The duration quote appears before you run. Failed runs release reserved credits.
No. Transcription runs after you accept the duration quote. The free dubbing preview belongs to dubbing mode, which uses different pricing.
No. ASR detects the spoken language automatically. The transcript stays in that language; transcription mode does not translate it.
No. The workspace displays timestamped segments but has no speaker reassignment or transcript editor. Download the files to make corrections in your editor.
No. Transcription delivers separate SRT, VTT and TXT files. It does not generate a new video or voice track.
Yes. Choose your file here, then sign in to upload it and continue in the workspace. Uploading does not automatically start a preview or a paid run.
No. File selection and upload do not start processing. Review the workspace quote and explicitly start the requested operation.
Choose your file, sign in and continue in the workspace. You decide when processing starts.
