Video Subtitles & Speech to Text - LexiTranscript

Upload a video or recording for AI transcription, then export SRT/VTT subtitles in one click. Your video stays on your computer - only the extracted audio is uploaded. Supports Chinese, Taiwanese, Japanese, English and more.

Drag and drop video or audio file here

or click to select file

Supported formats: .mp3, .wav, .m4a, .webm, .ogg, .flac, .aac, .wma, .opus, .mp4, .mpeg, .mpga, .mov, .mkv, .avi, .m4v

支援長達數小時的錄音轉錄,系統會自動優化音檔以確保最佳辨識效果。

Audio is extracted in your browser - the video file never leaves your computer

Speech to Text Features

Automatic Video Subtitles

Upload a video and get subtitles split by reading speed, exportable as SRT/VTT. Your video stays on your computer - only the audio is uploaded.

Fast Transcription

1 minute of audio transcribed in just 1-2 seconds - one of the fastest on the market

Multi-Language Support

Auto-detects Chinese, Taiwanese, English, Japanese, Korean and more

High Accuracy

Powered by OpenAI Whisper technology, achieving 97%+ accuracy in standard conditions

Timestamps

Automatic time marking for each segment, easy to reference original audio

AI Smart Summary

One-click summary generation to quickly grasp key points

Privacy Protection

Audio is not stored or used for AI training, ensuring your privacy

Use Cases

Meeting Minutes

Convert meeting recordings to text for quick minute generation

Interview Records

Transcribe interviews to save manual transcription time

Class Notes

Convert lecture recordings to text for automatic note-taking

Video Subtitles

Convert video audio to text for quick subtitle creation

Instructions

Supported Formats

Video: MP4, MOV, MKV, AVI, M4V, WebM. Audio: MP3, WAV, M4A, OGG, FLAC, AAC, WMA, Opus

File Size

Supports hours-long recordings. System automatically optimizes audio for best recognition.

Language Support

Supports 25 languages including Chinese, English, Japanese, Korean, Vietnamese and more

Processing Time

About 1-2 seconds per minute of audio

Frequently Asked Questions

How long does speech-to-text take?

Using TaiLexi AI speech-to-text, 1 minute of audio takes only 1-2 seconds to convert - one of the fastest transcription tools available.

What video and audio formats are supported? Can I upload a video directly?

Yes, you can upload video directly. Video: MP4, MOV (iPhone recordings), MKV, AVI, M4V, WebM. Audio: MP3, WAV, M4A, OGG, FLAC, AAC, WMA, Opus. Hours-long recordings are supported. When you upload a video, the audio track is extracted inside your browser and only that audio is sent for recognition - the video file never leaves your computer.

What languages are supported?

Supports Chinese (Mandarin), Taiwanese, English, Japanese, Korean and more. AI automatically detects the language in the audio.

Is the transcription accurate?

Powered by OpenAI Whisper technology, supporting 99 languages. Standard speech in low-noise environments achieves 97%+ accuracy.

Will uploaded audio be stored?

Absolutely not! AI only temporarily accesses audio during processing. It is not stored, not used for model training, and is deleted after processing to ensure your privacy.