We are seeking skilled Greek voiceover artists for an exciting project to create high-quality audio samples as we are developing a cutting-edge text-to-speech model. This exciting role requires producing 3 hours of clear, well-recorded voice samples, adhering strictly to our technical and quality guidelines.
Essential Requirements:
1. Recording Format: 48 kHz in Mono audio format.
2. Frequency: Ensure a minimum of 20 kHz. Recordings below this will be rejected. Your microphone and software must meet this requirement.
(Please review the attached image below. Ensure you self-check the audio quality using the Ocenaudio app. Share a screenshot of your audio analysis.)
3. Sound Quality: Audio must have NIL echo and be completely free from background noise or music.
4. Clipping: No instances of hard or soft clipping. (Include a picture as an example.)
5. Pronunciation: Clear and precise pronunciations are mandatory.
Please Note:- ADHERING TO THESE STRICT REQUIREMENTS IS CRUCIAL TO DELIVER THE HIGHEST QUALITY RECORDINGS FOR OUR ADVANCED TEXT-TO-SPEECH MODEL DEVELOPMENT
Preferred Practices:
1. Ensure no pauses within the speech and no heavy breathing for smooth, continuous recordings.
2. Clean up any retakes, click sounds, and lip-smacking.
3. Retain natural breathing sounds.
4. Maintain a normal speech pace without rushing.
Additional Information:
1. Type: Project-based, remote opportunity.
2. Suitability: Ideal for professional voiceover artists who can meet the above-mentioned technical standards.
Usage Rights:
The recorded samples will be used exclusively to train and improve our AI model. They will not be used for commercial audio reproduction, distribution, or as standalone copyrighted content. This project focuses solely on developing a high-quality AI model, ensuring your voice is only used for training.
PLEASE PROVIDE SAMPLE RECORDINGS THAT MEET THESE REQUIREMENTS ALONG WITH YOUR APPLICATION. WE LOOK FORWARD TO HEARING FROM YOU!