Free AI Speech to Text
Transcribe audio and video to text with 95+ language support. Get timestamps, speaker detection, and downloadable SRT/VTT subtitles.
Drop audio or video file here or click to upload
Supports MP3, WAV, M4A, MP4, MOV, WebM — up to 50 MB
Language
Transcribing your audio…
✓ Transcription complete!
Welcome to LubanAI, your free online toolkit for AI-powered media processing. Today we're demonstrating our speech-to-text feature, which uses state-of-the-art speech recognition to accurately transcribe speech in audio and video files. The transcription supports automatic language detection, speaker diarization, and multiple export formats including plain text, SRT subtitles, and VTT captions. Simply upload your file, choose your settings, and get results in seconds.
[00:00.000 --> 00:04.820] Welcome to LubanAI, your free online toolkit for AI-powered media processing. [00:05.100 --> 00:10.540] Today we're demonstrating our speech-to-text feature, which uses state-of-the-art speech recognition [00:10.540 --> 00:16.200] to accurately transcribe speech in audio and video files. [00:17.000 --> 00:22.350] The transcription supports automatic language detection, speaker diarization, [00:22.350 --> 00:27.800] and multiple export formats including plain text, SRT subtitles, and VTT captions. [00:28.100 --> 00:33.450] Simply upload your file, choose your settings, and get results in seconds.
Speaker 1 [00:00.000 --> 00:16.200] Welcome to LubanAI, your free online toolkit for AI-powered media processing. Today we're demonstrating our speech-to-text feature, which uses state-of-the-art speech recognition to accurately transcribe speech in audio and video files. Speaker 2 [00:17.000 --> 00:33.450] The transcription supports automatic language detection, speaker diarization, and multiple export formats including plain text, SRT subtitles, and VTT captions. Simply upload your file, choose your settings, and get results in seconds.
This result is temporary
Log in — it's free
You're signed out, so this result isn't saved and disappears when you refresh or leave. Log in to save your work, get daily free credits, and unlock premium models.
How It Works
1
Upload Audio or Video
Upload your audio or video file — supports MP3, WAV, M4A, MP4, MOV, and WebM up to 50 MB.
2
Select Language
Choose a language or use auto-detection. Optionally enable speaker detection for multi-speaker content.
3
Get Transcript
View results in plain text, with timestamps, or by speaker. Download as plain text, or as subtitles — SRT for video editors, VTT for web players.
Transcription Samples
Frequently Asked Questions
Upload your audio or video file to LubanAI. Our speech recognition model transcribes it automatically. Cost is tiered by length: 5 credits up to 5 minutes, 15 up to 15 minutes, 25 up to 30 minutes, and 50 up to 60 minutes. Free users get 10 daily credits.
We support MP3, WAV, M4A, MP4, MOV, and WebM files up to 50 MB. Both audio-only and video files with audio tracks are supported.
Accuracy depends on your audio. Clear speech in a widely spoken language transcribes almost word-for-word, while heavy accents, overlapping speakers, or background noise will lower it. Your free daily credits let you test your own files before paying anything.
Yes! Enable 'Detect Speakers' to identify and label different speakers in the transcript. This is great for interviews, meetings, and podcasts.
Absolutely. Download transcripts as plain TXT, SRT (for most video editors), or VTT (for web video players). Timestamps are automatically included.
Over 95 languages including English, Chinese, Japanese, Korean, Spanish, French, German, Arabic, Hindi, and many more. Auto-detection identifies the language automatically.
Typically about 2 seconds per minute of audio. A 10-minute recording takes roughly 20 seconds to transcribe.
Yes. LubanAI gives you free credits every day, with no monthly cap and no watermark on your transcripts, and TXT, SRT, and VTT export is included. You can start right away, without a subscription.