Voice · Setup in 8 min· Setup Pass

Set up ElevenLabs to read research in your own voice in 8 minutes

Configure a personal voice clone to convert dense medical studies and articles into audio you can listen to anywhere.

Reading research papers on a screen is fatiguing. This setup uses a clone of your own voice to convert text-based medical studies or health articles into audio files, creating a personal podcast for listening during a commute or workout.

Before you start

• An ElevenLabs account
• A computer with a microphone
• 3-5 minutes of quiet time to record audio
• A link to a research paper or article to convert

The steps

1. 01

   Clone your voice

   In the Voice Lab, select "Add Generative or Cloned Voice," then "Instant Voice Cloning." Record or upload at least one minute of clear, evenly-paced speech. Read from a neutral text like a Wikipedia article, avoiding overly emotional delivery.

2. 02

   Generate your first audio file

   Go to the "Speech Synthesis" tool. Select your newly cloned voice from the dropdown menu. Paste in a short block of text, such as the abstract of a medical study, and click "Generate."

3. 03

   Fine-tune the voice settings

   Listen to the output. If it sounds robotic or flat, adjust the "Voice Settings." For technical content, slightly increasing "Clarity + Similarity Enhancement" and decreasing "Stability" can improve naturalism without sacrificing accuracy.

4. 04

   Convert a full-length article

   For documents longer than the character limit, use the Projects tool. Paste the full text and the tool will generate and stitch together multiple audio segments. This is the most efficient method for turning a full research paper into an audio file for your "Ledger" of personal health information.

5. 05

   Manage your audio library

   Generated files appear in your "History." Download the MP3s and give them systematic names (e.g., "AuthorYear_Topic_YYYY-MM-DD.mp3"). This creates a searchable audio library of your research that you can sync to your phone.