Frequently asked questions
What audio and video formats are supported?
Most common formats work out of the box, including MP3, WAV, M4A, FLAC, OGG, MP4, MOV, and MKV.
Can I import a file from Google Drive instead of uploading it?
Yes, on the Pro plan. Paste a Google Drive share link (or pick a private file straight from Drive) and Listently fetches it directly — no download-then-upload roundtrip.
How accurate is the transcription?
Accuracy is high for clear audio in well-supported languages, and drops on very quiet, fast, or overlapping speech — the same tradeoff every automatic transcription tool makes. We keep working on reducing this gap.
How does speaker detection work, and can I rename speakers?
Each distinct voice is automatically detected and labeled. You can rename any speaker to their real name at any time, and the change applies across the whole transcript and its AI summary immediately.
What languages can I transcribe in?
Over 100 languages are supported for transcription, from major world languages to many regional and less-common ones.
What's included in Free vs Pro?
Free includes 3 transcriptions per day, up to 30 minutes per file, and 2GB uploads. Pro removes the daily limit and file-length limit, and raises the upload size to 5GB. See the pricing page for the full comparison.
Full pricing comparison →Can I upload multiple files at once?
Yes, on Pro — select or drag up to 10 files at once and each becomes its own transcript, with progress shown per file as they process. Free plans upload one file at a time.
Can I set up a custom vocabulary for names, jargon, or acronyms?
Yes. Save a personal list of terms — names, product names, technical jargon, acronyms — in your profile, and Listently uses it to bias transcription toward the correct spelling on every file you transcribe afterward. Free plans can save up to 15 terms; Pro plans up to 50.
Is my audio ever used to train AI models, or shared with third parties?
No. Your audio and transcripts are never used to train any AI model, and are never shared with third parties.
What export formats are available?
Transcripts can be exported as Word documents, PDFs, or subtitle files (SRT/VTT).
How does the AI summary work — is it accurate?
The summary is generated from the actual transcript text and attributes points to specific speakers. It's instructed not to invent action items or conclusions that aren't actually present in the conversation.
Can I edit the transcript after it's generated?
Yes — transcript text and speaker names can both be edited after transcription completes.
Can I remove filler words like "um" and "uh" automatically?
Yes, on Pro. A one-click toggle hides filler words from the on-screen transcript and from your exports, without changing the original — turn it off any time to see the verbatim version again.
Can I highlight text and leave comments on a transcript?
Yes, on Pro. Select any text to mark it in one of 5 colors and/or attach a private comment — useful for flagging quotes or moments to come back to.
How do I contact support or leave feedback?
From inside the app, use the support button in the bottom-right corner of any page to leave feedback or ask a question — we typically reply within 24 hours.