Voice recording to text
Voice recording to text for memos, calls, and more
Hushscript is a voice recording to text converter for existing files: it turns a voice memo, call recording, voicemail, or dictation file into editable, timecoded text. It removes its transcription audio after processing and never trains on your recordings. Preview up to 5 minutes before creating an account, then correct speaker labels in the browser app and export the transcript.
Drop an audio or video file to preview your transcript
First 5 minutes preview
Choose a fileVideo stays local. Transcription audio isn't kept.
Paste a shared link to an audio file. How link import works
Record up to 5 minutes with your microphone. Nothing uploads until you choose to transcribe.
No sound from the microphone. Check that it is on and not muted.
Saved in your browser's recording format. Need MP3 or WAV? Convert it with Hushscript's free audio converter
Check your email for your sign-in link. It's valid for 15 minutes.
This preview stays on this page and isn't carried into the app. Sign in and choose your file again; a new personal account's first upload gets its own free preview of up to 5 minutes. Full transcription needs enough available minutes. Eligible personal accounts can receive 30 free minutes once after successful card verification, or with their first purchase if not already granted.
How it works
- 01
Add the voice recording
Choose one supported audio file, such as a voice memo, call recording, or voicemail. Recordings can run up to 10 hours.
- 02
Preview or record up to 5 minutes
Check the transcript and automatic speaker labels before creating an account. The preview uses automatic language detection; full transcription controls are available in the app.
- 03
Create the full transcript
Sign in, merge related parts in your chosen order if needed, and choose the full transcription options. Eligible accounts get 30 free minutes once, after card verification or with a first purchase.
At a glance
- Price
- Packs from $1.99, about $0.50 per hour of audio on the largest pack
- Transcription length
- Up to 10 h per file
- Upload limit
- No file size limit
- Languages
- 99 languages
- Privacy
- Hushscript removes its transcription audio after processing, never trains on your recordings, and encrypts stored transcripts at rest.
Voice recording to text makes a voice memo, recorded call, voicemail, or other spoken recording searchable and editable. Hushscript sends prepared audio for online speech recognition, then lets you review the timecoded, speaker-labeled transcript in the browser before you export it. In the full app after sign-in, related clips can also become one ordered transcript instead of separate files.
How to transcribe a voice memo to text
To convert an audio recording to text, add the original recording, preview up to 5 minutes before creating an account, then sign in for the full transcript. Supported M4A audio can upload unchanged, so a voice memo does not need an MP3 copy first. In the editor, correct the words and speaker names, then export in 21 formats, including TXT, DOCX, PDF, SRT, and VTT.
Voice to text converter online for an existing recording
Hushscript uses AI automatic speech recognition to turn recorded speech into an editable draft. It works with existing voice memos, calls, voicemails, field notes, and recorded dictation in supported formats. This is online transcription of a recording, not live dictation or voice typing. Clear, close speech is easier to transcribe than distant voices, background noise, or overlapping speakers, so preview your own recording and review the result.
Calls, voicemails, and recordings in parts
Speaker detection is available across the supported transcription languages at no extra minute cost, but automatic labels can be wrong. Rename display names, reassign an individual turn, or split and merge transcript turns as you review a recorded call. In the full app after sign-in, merge related clips in your chosen order; review speaker labels across the joins rather than assuming the same label always identifies the same person.
Transcribe or translate a voice recording
“Translate voice to text” can mean transcribing spoken words or translating the written transcript into another language. Hushscript transcribes roughly 99 spoken languages. The preview uses automatic language detection, while the full app also lets you choose the source language. For written translation, select from 13 targets before transcription, each adding 25% of the recording duration. Translation-target jobs use personal minutes for the entire transcription, including in a Teams workspace. The result is translated text, not live interpretation or dubbed audio.
Record first, then transcribe
The preview Record tab captures up to 5 minutes in the browser before you choose to transcribe the recording to text. For a longer recording, the free voice recorder captures up to 10 hours locally, requires no account, and does not upload the recording. Save the browser’s original recording at any length; on-page WAV conversion is available up to 30 minutes and MP3 conversion up to 2 hours. Hushscript is not a phone voice-memo app or a live dictation tool. If you only need to change an existing file’s format, use the free browser-based conversion tools.
Privacy controls for sensitive recordings
Hushscript removes the transcription-audio copy after processing and does not use recordings to train models. Stored transcript content, titles, speaker metadata, translations, and Insights artifacts are encrypted at rest, with retention controls for the saved transcript. Private mode still uses online speech recognition, but saves no transcript to the account and runs no translation, medical mode, or Insights. A short-lived encrypted result lets the browser build the password-protected archive.
Personal pay-as-you-go transcription
Personal accounts use prepaid minutes. Hushscript for Teams is a separate monthly or annual offer, and optional translation uses personal minutes rather than pooled Teams hours. The pricing page lists the personal packs.
Updated:
Why Hushscript
Private by design
Transcription audio is deleted after processing, recordings never train models, and stored transcripts are encrypted at rest. Use private mode to save no transcript to your account.
Speaker labels you can correct
Rename speakers, reassign individual turns, or split and merge transcript turns in the editor.
No subscription
Pay-as-you-go: buy minutes only when you need them. Nothing recurring, nothing to cancel.
Frequently asked questions
How do I transcribe a voice memo?
Add the original supported recording, preview up to 5 minutes, then sign in for the full editable transcript. A supported M4A voice memo can upload unchanged, so converting it to MP3 first is not required.
Which recording formats and lengths work?
Hushscript accepts common formats including M4A, MP3, WAV, FLAC, OGG, and Opus. A recording can run up to 10 hours; format support, device capacity, and service safeguards still apply.
Can I turn a voice recording or voice memo into text for free?
Yes, to start: the preview works as a free voice to text converter for up to 5 minutes with no account, and eligible accounts get free starter minutes. After that it is pay-as-you-go.
Can I record in the browser first?
Yes. The transcription preview can record up to 5 minutes. The separate free voice recorder stays on your device and records up to 10 hours; Save a copy works at any length, while WAV conversion is available up to 30 minutes and MP3 conversion up to 2 hours.
Are both sides of a recorded call labeled?
Speaker detection separates a recording into labeled turns, but overlap, distance, and weak audio can cause mistakes. Review the labels; you can rename speakers, reassign individual turns, and split or merge transcript turns.
Is Hushscript a dictation app?
Not for live dictation. Hushscript transcribes a recording you already have, such as recorded dictation, a voice memo, a voice note, or a voicemail, and returns editable text. It is a voice to text converter for files, not a keyboard microphone.
Can I translate a voice recording?
Hushscript transcribes roughly 99 spoken languages and offers 13 written translation targets in the app, each adding 25% of the recording duration. A translation-target job uses personal minutes for the whole transcription, including in a Teams workspace; it is not live translation or dubbed audio.
What's the difference between normal mode and private mode?
Normal mode saves an encrypted transcript in your account with retention controls. Private mode still uses online speech recognition, but saves no transcript to the account and runs no translation, medical mode, or Insights; a short-lived encrypted result lets the browser create a password-protected archive.
Start with 30 free minutes
Preview up to 5 minutes before you create an account, and a new personal account gets a free preview of its first upload in the app. Full transcription needs an account and minutes; eligible personal accounts get 30 free minutes once, after card verification or with a first purchase. No subscription.
Get 30 free minutes