AI-Powered Transcription

Transcribe Audio & Video to Text

AI audio and video transcription with stronger recognition across 30 primary languages. Some other languages are supported with potentially higher error rates.

3GP, AAC, AMR, AWB, FLAC, M4A, MKA, MKV, MOV, MP2, MP3, MP4, MPG, OGA, OGG, OPUS, TS, WAV, WEBA, WEBM, WMA, WMV

Three steps to your transcript

A fast, simple workflow

01

Upload your file

Drag and drop audio or video files directly in your browser. Supports 22 formats up to 2GB.

02

AI transcribes

Advanced AI processes your file with speaker detection and timestamps. Usually done in minutes.

03

Edit & export

Review and refine online, then export to TXT, PDF, DOCX, SRT, CSV, or VTT.

Export anywhere, any format

Download your transcripts in the format that works for your workflow. From simple text files to professional subtitle formats — we've got you covered.

  • TXT, PDF, DOCX for documents
  • SRT, VTT for subtitles
  • CSV for data analysis
.TXT
.PDF
.DOCX
.SRT
.VTT
.CSV

Simple, transparent pricing

Start free. Upgrade when you need more.

Free

Free

No credit card required

  • 120 minutes per month
  • 3 files per day
  • Each file can be up to 30 minutes long
  • Basic exports (TXT)

Pay as you go

$9.9 one-time
  • 1200 minutes included
  • AI summaries & mind maps
  • No daily upload limit
  • All export formats
  • Speaker diarization
  • API access
  • Priority support

Pro

$10 /mo

  • 2000 minutes per month
  • Up to 3 translations per task
  • AI summaries & mind maps
  • No daily upload limit
  • All export formats
  • Speaker diarization
  • API access
  • Priority support

Max

$20 /mo

  • 4800 minutes per month
  • Unlimited translations
  • AI summaries & mind maps
  • No daily upload limit
  • All export formats
  • Speaker diarization
  • API access
  • Priority processing
  • Priority support

Need enterprise features? We offer private deployment, custom integrations, and dedicated support. Contact us

Frequently asked questions

What file formats does UUScribe support?
UUScribe supports 22 audio and video formats including MP3, WAV, M4A, FLAC, MP4, MOV, MKV, WEBM, and more. Each file can be up to 12 hours long (Free: 30 minutes per file), and audio files can be up to 2 GB. On desktop browsers, videos are converted to audio by default before upload; mobile browsers upload the original video, which must also fit within 2 GB. For faster uploads, we recommend converting videos to audio yourself first.
How many languages are supported?
UUScribe primarily supports these 30 languages, with generally higher recognition accuracy: Chinese, English, Japanese, Korean, Vietnamese, Thai, Indonesian, Malay, Filipino, Hindi, Arabic, French, German, Spanish, Portuguese, Russian, Italian, Dutch, Swedish, Danish, Finnish, Greek, Polish, Czech, Hungarian, Romanian, Bulgarian, Croatian, Slovak, and Norwegian. Some other, less common languages are also supported, but may have higher error rates. Accuracy also depends on recording quality, accents, and background noise.
Is there a free plan?
Yes. The Free plan includes 120 minutes of transcription per month, supports 3 files per day (up to 30 minutes each), and basic TXT exports. No credit card is required.
Can I transcribe YouTube videos?
Yes. Paste any YouTube URL and UUScribe will generate a full transcript with timestamps and optional subtitles in SRT or VTT format.
Does UUScribe offer an API?
Yes. Pro, Max, and Pay as you go customers can use the REST API with token authentication, file uploads, task management, and transcript retrieval. The Free plan does not include API access.
Is my data private and secure?
Yes. Uploads are encrypted in transit and at rest. Original audio is retained for 365 days by default; signed-in users can choose a shorter period or never automatically delete it. Transcripts, summaries, and exports remain until you delete them. Approved third-party cloud and AI providers may process data under contractual privacy obligations. See our Privacy Policy for full details.
How long should recordings be for speaker diarization?
For speaker diarization, we recommend recordings of 2 hours or less. Longer recordings may produce less accurate speaker labels. This is a quality recommendation, separate from the 12-hour maximum file duration.