Private, pay-as-you-go transcription
No account required to try. Files auto-delete after 24 hours. Your audio is never used to train AI models.
Drag a file here or browse
MP3, WAV, M4A, FLAC · MP4, MOV, MKV, WebM · up to 2 GB
Set language, translation, or vocabulary hints below before transcribing
YouTube, Dropbox, Google Drive, or any direct MP3/MP4 link
Transcription model
Transcript style
Removes fillers and false starts for readable text
Names, acronyms, or domain terms that improve accuracy
MP3, WAV, M4A, FLAC · MP4, MOV, MKV · up to 2 GB · 10 free minutes every day
How privacy works here
No account needed to try
Upload a file and get a transcript without creating an account or entering an email address. An anonymous session cookie links your browser tab to the job so you can reload the results page. Signing up is optional — it adds a persistent daily 10-minute free quota and a transcript history, nothing more.
Files auto-delete after 24 hours
Audio files and generated transcripts are deleted from convert.express storage 24 hours after your last activity. If MAI speaker labeling is enabled, pyannoteAI's temporary Media API copy is deleted within 48 hours. Download your transcript before the convert.express window closes.
Your audio is never used for AI training
Files sent to the transcription API you select — OpenAI Whisper, Microsoft MAI-Transcribe 2, or Google Gemini 3.5 Transcribe — are processed under that provider's API terms of service, which explicitly prohibit using API inputs to train their models. convert.express does not use your audio, transcripts, or any personal data for advertising, profiling, or model training of any kind. See the privacy policy for the full data-handling breakdown.
No third-party sharing beyond delivery
Your audio is shared with the selected transcription API and temporary storage. MAI speaker labeling also uses pyannoteAI for a whole-file diarization pass. No data is sold. Payments go through Stripe; your card details are never stored on our servers.
Who this matters for
Not every transcription job carries the same risk profile. A public conference keynote is different from a source interview, a deposition, or a clinical consultation. The privacy defaults on this service — no accumulation, no training, 24-hour deletion — are designed for the latter category.
- Journalists — source calls and field interviews where recording confidentiality matters.
- Lawyers — depositions and client calls where a fast first-pass draft is needed before formal transcription.
- Clinicians — post-consultation dictation notes that need to reach the EHR without persisting on a third-party platform.
- HR professionals — interview recordings, disciplinary meetings, or sensitive internal conversations.
- Researchers — qualitative interviews with participants under IRB confidentiality requirements.
The honest trade-off
The 24-hour auto-delete is a privacy feature, not a limitation. Your files don't sit on a server waiting to be breached, subpoenaed, or quietly kept longer than you expected. In practice that means download your transcript before the window closes — if you'll need it days later, save a copy to your own system now. There's no recovery option for a deleted job. That's deliberate.
Frequently asked questions
Can I transcribe audio without creating an account?
- Yes. convert.express uses an anonymous session cookie to link your uploaded file to your browser tab. You can upload, transcribe, and download the result without creating an account or providing an email address. Creating a free account simply gives you a persistent daily 10-minute quota and access to your transcript history across sessions.
How long are my files kept after transcription?
- Audio files and transcripts in convert.express storage are automatically deleted 24 hours after your last activity on the job. If you enable speaker labels with MAI-Transcribe 2, pyannoteAI retains its temporary Media API audio copy for up to 48 hours. If you have not downloaded your transcript within 24 hours, it will no longer be accessible from convert.express.
Is my audio used to train AI models?
- No. Files sent to the transcription API you select — OpenAI Whisper, Microsoft MAI-Transcribe 2, or Google Gemini 3.5 Transcribe — are not used to train that provider's models under its API terms of service. convert.express does not use your audio for any purpose beyond transcribing it and returning the result. We do not use your data for advertising, profiling, or model training. See the full privacy policy for details.
What happens to my transcript if I forget to download it?
- It is deleted. The 24-hour auto-delete applies to both the audio file and the generated transcript, and it is not reversible — nobody on our side can pull it back for you afterward. So download it before closing the tab, or at least note the job URL so you can return within the 24-hour window.
Do you share my recordings with anyone?
- Your audio is shared with the transcription API you select and a temporary cloud storage provider. MAI-Transcribe 2 speaker labeling also sends the normalized audio to pyannoteAI for a whole-file diarization pass. No provider uses your audio for model training under its API terms. No data is sold. Payments are handled by Stripe; we never see or store your card details.
Is this suitable for confidential recordings — interviews, legal calls, medical notes?
- The automatic 24-hour deletion and no-training policy make it reasonable for source-sensitive journalism, research interviews, and working drafts of legal or clinical notes. It is not a HIPAA Business Associate and does not sign BAAs. For recordings subject to formal legal or regulatory requirements, verify your organisation's compliance guidance before use and treat AI output as a working draft requiring human review.
Try it without an account
Upload a file now — the first 10 minutes are free. No email required.
Transcribe privately →See also: pricing · AI models · privacy policy