Transcribly

Transcribe and summarize audio & video content

Configuration

Provide your API credentials and preferred models. Leave the API key blank to use backend defaults.

API Key

Stored locally only for this session. Leave blank if the backend manages credentials.

Transcription Provider

Choose between OpenAI Whisper or AssemblyAI for speech-to-text processing.

Speech-to-Text Model

Next-gen GPT-4o transcription model with enhanced quality.

Summarization Model

Summary Max Tokens

Choose your preferred method to upload audio or video content for transcription

Drag & drop your audio file

or click to browse files

Supports MP3, WAV, and MP4 files

View and download your transcript and summary

Upload a file or paste a YouTube URL to get started