Transcribe Audio

26 Jan Transcribe Audio

The “Transcribe Audio” feature is a transformative tool that harnesses the power of artificial intelligence to automatically convert spoken content within audio files into accurate and readable text. By employing advanced speech recognition algorithms, this feature ensures precise transcription, capturing nuanced details and accurately transcribing diverse audio content. From podcasts and interviews to business meetings, the AI-driven “Transcribe Audio” capability not only saves time but also enhances accessibility by providing a reliable and efficient solution for converting spoken words into written form.

The following AI providers support “Transcribe Audio” feature. It means that you should put their API credentials (at least for one of them) on Settings page to have this feature available.

• AssemblyAI
• Deepgram
• Gladia
• OpenAI

Step-by-step instruction how to use “Transcribe Audio” feature.

1. Make sure that you put valid API credentials for AI provider, which supports transcribing audio.
2. Go to Media Library, select audio file and find “Green AI Assistant” metabox.
3. Click “Transcribe Audio”.
4. Select desired AI provider and complete simple form to adjust transcribing parameters (if available).
5. Click “Transcribe Audio” button. The process takes some time. When it’s finished you can review transcription.

The video below explains how to use “Transcribe Audio” feature.