Audio files, readable words
Audio to Text Converter
Turn a recording into text you can search, edit and keep. Upload an audio file, then listen back while you check the words.
- Start with 10 minutes, no sign-up or card
- Edit every line beside its audio timestamp
- Download TXT free; get SRT, VTT, DOCX with a paid plan
Drop your audio file here
No sign-up · first file up to 10 min · MP3, WAV, M4A, AAC, OGG, FLAC
Transcribe audio to text in your browser — MP3, WAV, M4A, AAC, OGG, FLAC
How it works: start with the recording already on your device. There is no link to paste and no software to install. The browser prepares your file for upload; the transcription service turns the speech into words. Only audio is sent for transcription.
- Choose the audio recording. Drop an MP3, WAV, M4A, AAC, OGG or FLAC file into the upload box, or choose it from your device. Keep the original recording nearby so you can check unfamiliar names later. You upload the audio file itself, without needing to create a video around it.
- Let Voxcribe detect the language. Language detection runs automatically when transcription starts. You do not have to name the language before trying a recording. Clear speech is easier to review than a room full of overlapping voices, so use the cleanest recording you have. Transcription happens on the service after the browser prepares the audio.
- Listen and correct the text. Open the timestamped editor when the result is ready. Select a line to hear that moment again, then fix names, punctuation or a phrase the recording made hard to hear. Listening beside the text helps you check the intended wording without repeatedly searching through the whole file.
- Keep the version you edited. Export the corrected transcript when you finish reviewing it. Choose a plain text file for notes, or a paid export format when you need subtitles or a document. Check the last few lines before downloading, especially if the recording ends halfway through a sentence.
Audio formats and recording limits
MP3, WAV, M4A, AAC, OGG and FLAC use the same plan limits. The recording length, rather than its filename extension, determines how much transcription time it needs. A compressed MP3 and an uncompressed WAV of the same conversation both use the duration of that conversation.
| Audio formats and recording limits | Without account | Free account | Starter | Pro | Business |
|---|---|---|---|---|---|
| Per-file limit | 10 min | 30 min | 180 min | 600 min | 600 min |
| Monthly minutes | No monthly allowance | 120 min | 1200 min | 3000 min | 6000 min |
| Daily files | 1 | 3 | No daily limit | No daily limit | No daily limit |
| Export formats | TXT, copy | TXT, copy | TXT, copy, SRT, VTT, DOCX | TXT, copy, SRT, VTT, DOCX | TXT, copy, SRT, VTT, DOCX |
| Text retention | 7 days | 30 days | Until you delete it | Until you delete it | Until you delete it |
The first file without an account can be up to 10 minutes. A free account includes 120 minutes each month, with recordings up to 30 minutes and 3 files a day. If your recording is longer, compare pricing and free limits before you begin. The table describes transcription and text storage; the separate audio deletion period is explained below.
Choose text, a document or subtitle files
The right download depends on what you want to do with the words. A transcript for your notes does not need the same packaging as captions for an editing timeline. Review the transcript first, because the downloaded file uses your edited wording.
TXT downloads are included in the free plan. Use plain text when you want to paste a passage into your notes, search a recording later or move the words into another writing tool. Copying the transcript is available too.
Paid plans add SRT, VTT, DOCX. A document export is useful when the transcript needs to travel with a draft. Subtitle exports split the text into timed cues: at most two lines, up to 42 characters per line, with cues lasting 1–7 seconds.
Voxcribe creates subtitle files; it does not burn captions into a video. Import the subtitle file into your editor or player separately, then check its appearance there. Exporting subtitles does not create a finished video or replace your original recording.
Voice memos & iPhone recordings (.m4a)
A quick recording often starts as a reminder to yourself. When those reminders build up, converting a voice memo to text gives you words to search instead of a list of filenames to replay.
On an iPhone, share the recording from Voice Memos and save the .m4a file to Files. Open Voxcribe in your browser, choose that saved file and begin. You can upload the .m4a directly; you do not need to convert it to MP3 first.
The same workflow works for a voice recording to transcript when the file comes from another recorder. For m4a to text, choose the actual recording from your device rather than a sharing link. Once the words arrive, check shorthand, place names and any sentences you spoke too quickly to finish.
Recordings you may want to revisit
Use an audio transcript as a working copy of what was said. It helps you find a passage, but you should still listen to the source before treating a quotation or an unfamiliar term as final.
Personal voice memos
Capture an idea while walking, then turn the recording into a rough draft at your desk. Remove false starts and keep the useful phrases in your own notes.
Meeting recordings
Find the moment a task or decision came up without replaying the entire meeting. Check the recording before assigning a comment to someone, and share only what you are allowed to share.
Recorded classes
Search the wording around a topic you want to revisit. Listen again when a technical term is unfamiliar, then correct it in the transcript before using the text as study notes.
Interview audio
Use timestamps to locate a quotation and hear the surrounding answer. Voxcribe does not currently distinguish speakers, so review the conversation yourself and add names manually where you need them.
What happens to your audio and text
Only audio is uploaded for transcription. Browser processing prepares the sound before it is sent; it does not mean the speech recognition runs offline on your device. Keep that distinction in mind when choosing which recordings to upload.
Uploaded audio is deleted after 7 days. Anonymous transcript text is kept for 7 days, while free-account text is kept for 30 days. Paid-plan text is kept until you delete it. Download a copy if you need the transcript outside that retention window.
We do not use your recordings or transcripts to train transcription or AI models. See the privacy policy for how recordings and account data are handled. Before uploading a meeting, class or interview, make sure you have permission to process that recording.
Audio transcription questions
A few details to check before choosing a recording.
Is it free?
Yes. Start without an account with a file up to 10 minutes, with 1 file a day. A free account includes 120 minutes per month, 3 files a day and a 30-minute per-file limit. TXT is free; longer allowances and SRT, VTT, DOCX exports need a paid plan. You do not need a card to try the free option.
Can I convert MP3 to text?
Yes. Choose an MP3 from your device or drop it into the upload box. Voxcribe prepares the audio in the browser, detects its language and returns editable text with timestamps. You can also upload WAV, M4A, AAC, OGG or FLAC, so there is no need to change a supported recording to MP3 first.
Is there a length limit?
Yes. Without an account, the per-file limit is 10 minutes. A free account allows 30 minutes per recording within its 120-minute monthly allowance. Paid plans have larger limits, shown in the table above. Compare the duration of your recording with both the per-file cap and the minutes remaining in your plan before starting.
Can I export SRT?
Yes, with a paid plan. Paid downloads include SRT, VTT, DOCX, while TXT is available free. SRT and VTT contain timed subtitle cues based on the transcript. Review the words before exporting, then import the subtitle file into your editing or playback tool. Voxcribe creates the file; it does not embed the captions in a video.
Does it label speakers?
Not yet. The transcript does not automatically separate or name speakers. For a conversation or interview, listen at each timestamp and add the names yourself. If voices overlap or several people speak quickly, take extra care when checking who said a particular sentence before quoting it.
Do you keep my audio?
Uploaded audio is deleted after 7 days. Transcript text has a separate retention period: 7 days for anonymous use, 30 days with a free account, and until you delete it on paid plans. Download your edited text if you want to keep it locally. We do not use your recordings or transcripts to train transcription or AI models.