ManualTrigger Automate

This workflow is ideal for:

• Content Creators: Individuals or teams producing audio or video content who need to transcribe spoken words into text efficiently.
• Developers: Those looking to integrate speech-to-text capabilities into their applications or services using Eleven Labs API.
• Researchers: Professionals needing to convert interviews or discussions into written format for analysis and reporting.
• Businesses: Organizations that require accurate transcription of meetings, webinars, or customer interactions for documentation purposes.

This workflow addresses the challenge of converting audio files into text format seamlessly. It automates the process of:

• File Handling: Reading audio files from disk.
• Transcription: Utilizing Eleven Labs API to convert audio into text, eliminating the need for manual transcription.
• Efficiency: Reducing time and effort spent on transcription tasks, allowing users to focus on more critical activities.

1. Manual Trigger: The workflow starts when the user clicks the ‘Test workflow’ button, initiating the process.
2. Read/Write Files from Disk: The specified audio file (/files/tmp/tst1.mp4) is read from the disk, preparing it for transcription.
3. Create Transcript1: The workflow sends a POST request to Eleven Labs API with the audio file and the model ID (scribe_v1) to generate a text transcript of the audio content. The request includes necessary headers and authentication details.