Frequently Asked Questions
Answers to common questions about XingYu audio-to-text transcription.
What audio formats does XingYu support?+
MP3, WAV, M4A, AAC, FLAC, OGG, OPUS, AMR, WMA, AIFF and more. You can also record directly with your microphone and transcribe it.
What is the maximum audio length per file?+
Free plan supports up to 30 minutes per file; Pro has no per-file duration limit. Uploads and recordings share your monthly quota.
Can it separate different speakers?+
Yes. Transcripts are generated with speaker diarization, shown as a conversation between Speaker 1 / Speaker 2, each with timestamps.
Do transcripts include timestamps?+
Every segment carries a timestamp. Click any segment and the audio jumps to that position, so you can proofread while listening.
What export formats are available?+
Pro users can export TXT, SRT and VTT. SRT and VTT work directly as video subtitles.
Do you support bilingual subtitles?+
Yes. Pro users can generate bilingual subtitles (choose any two languages, e.g. Chinese + English) and can desensitize the transcript to hide phone numbers, emails, and ID numbers.
What is the difference between Free and Pro?+
Free gives 60 minutes/month, up to 30 min per file, results kept 30 days. Pro ($4.99/mo) gives 1200 minutes/month, no per-file duration limit, copy/bilingual subtitles/desensitization/export, permanent results, and 365-day audio retention.
How long are audio and transcripts kept?+
Free: transcripts 30 days, original audio 7 days. Pro: transcripts permanently, original audio 365 days.
Does recording immediately consume quota?+
No. Recording itself does not consume quota — quota is deducted only when you click “Transcribe”.
Is my data safe?+
Audio is stored in encrypted storage and transcription runs on a server-side queue. Your files are private to your account and can be deleted anytime.
Still have questions?