AI Speech to Text

Transcribe audio and video to text with 95+ language support. Get timestamps, speaker labels, and downloadable SRT/VTT subtitles.

Drop audio or video file here or click to upload Supports MP3, WAV, M4A, MP4, MOV, WebM — up to 300 MB
Settings
Language
Labels who is speaking in the transcript. Suited to interviews, meetings and podcasts.
Results kept 7 days · tied to this browser — Sign in to access them across devices
Loading tasks…
Updates paused · Retrying

How It Works

1
📤

Upload Audio or Video

Upload your audio or video file. Supports MP3, WAV, M4A, OGG, FLAC, MP4, MOV, and WebM — up to 300 MB and 60 minutes.

2
🌐

Select Language

Choose from common languages or use auto-detection. Enable speaker detection for multi-speaker recordings like interviews and meetings.

3
📄

Get Your Transcript

View your transcript as plain text, with timestamps, or sorted by speaker. Export as TXT, SRT (for video editors), or VTT (for web players).

Frequently Asked Questions

Upload your audio or video file to LubanAI — the AI transcribes it automatically. A free account is required. Cost depends on length: 4 credits for up to 5 minutes, 12 for up to 15 minutes, 23 for up to 30 minutes, and 46 for up to 60 minutes. Signed-in free accounts get 10 free credits daily, enough to transcribe a short recording. If a paid transcription fails, your credits are refunded automatically.

Yes. Upload the video file directly; there is no need to extract the audio first. MP4, MOV and WebM videos are transcribed from their audio track, up to 60 minutes per file. Download the transcript as plain text (TXT) or as SRT or VTT subtitles with timestamps, ready for YouTube, TikTok or course videos. Pricing starts at 4 credits for up to 5 minutes.

MP3, WAV, M4A, OGG, FLAC, MP4, MOV, and WebM files up to 300 MB. Both audio-only files and videos with an audio track are accepted.

Yes. Download your transcript as TXT (plain text), SRT (for most video editors), or VTT (for web players). Timestamps are included automatically.

LubanAI transcribes speech in 95+ languages, including English, Chinese, Japanese, Korean, Spanish, French, German, Portuguese, Arabic and Hindi. The language is set to auto-detect by default, which identifies the spoken language, so most files need no setting. You can also choose one of the languages listed above before you start.

Accuracy depends on your audio quality. Clear speech in a widely spoken language transcribes near word-for-word; heavy accents, overlapping speakers, or background noise will reduce it. Use your free daily credits to test your own files before purchasing more.

Yes. Enable 'Detect Speakers' and the AI will identify and label each speaker in the transcript — ideal for interviews, meetings, and podcasts.

Yes. Transcripts and subtitle files can be used commercially, including published articles, video subtitles, show notes and client work. No attribution is required on paid plans or credit packs; free-plan outputs require attribution to LubanAI. Make sure you own or have permission to use the recordings you upload.

Transcripts and the audio or video you upload are available for 30 days (7 days for free accounts). After that, they can no longer be downloaded, so save the TXT, SRT or VTT files you need before the retention period ends. See the Privacy Policy for details on how files are handled.

Yes, for short recordings. Signed-in free accounts get 10 free credits every day, and a file of up to 5 minutes costs 4 credits. Longer files, up to 60 minutes each, are priced by length and paid with credits, with no subscription required. Every transcript downloads as TXT, SRT or VTT, and the Detect Speakers option labels who is speaking in interviews and meetings.

Tasks are processed in the order they are submitted. Paid tasks from subscribers and credit pack buyers are picked up first. Free tasks may wait longer during peak hours.

We use cookies to improve your experience. See our Privacy Policy.