This role is for one of our clients
Compensation: $50 per hour
Join an innovative AI research initiative focused on developing next-generation text-to-speech (TTS) systems capable of producing natural, expressive, and human-like voices. We are seeking experienced voice professionals with authentic Southern American English accents to contribute high-quality voice recordings used to train and evaluate advanced speech generation models.
This opportunity is ideal for voice actors, narrators, broadcasters, and other audio professionals who can consistently deliver clear, engaging, and emotionally expressive performances across a variety of scripts.
Important: Voice recordings will be used exclusively to support an internal customer experience (CX) AI agent. Recordings will not be sold, licensed, or repurposed for unrelated products or datasets.
Requirements
Key Responsibilities
Record Professional Voice Samples
- Record high-quality audio across a variety of script types, including conversational, narrative, instructional, and customer interaction scenarios.
- Deliver natural, expressive speech with excellent control of tone, pacing, pronunciation, and clarity.
- Maintain consistent voice quality, accent, and delivery throughout multiple recording sessions.
Follow Recording Standards
- Adhere to detailed recording guidelines regarding recording environment, microphone setup, audio quality, and file formatting.
- Produce multiple takes with different emotional styles, emphasis, or delivery when requested.
- Ensure recordings are clean, free from background noise, and meet project quality standards.
Required Qualifications
- Native Southern American English speaker currently residing in the United States.
- Authentic Southern U.S. accent (including regions such as Texas, Georgia, Tennessee, North Carolina, South Carolina, Louisiana, Alabama, Mississippi, or similar).
- Professional experience in voice acting, narration, broadcasting, dubbing, podcasting, or related voice-based work.
- Access to a professional or near-professional home recording setup, including:
- High-quality microphone
- Quiet recording environment
- Pop filter or equivalent equipment
- Strong vocal control with excellent diction, pronunciation, intonation, and emotional range.
- Ability to accurately follow scripts while maintaining a natural and engaging delivery.
- Availability to contribute 5–10 hours per week during the project period (approximately 1–2 weeks).
Preferred Qualifications
- Experience recording content for text-to-speech systems, AI speech datasets, audiobooks, IVR platforms, or voice assistants.
- Familiarity with audio editing software such as Audacity, Adobe Audition, Reaper, or similar tools.
- Ability to perform multiple vocal styles, including conversational, professional, energetic, calm, and instructional tones.
Important Information
- Voice recordings may be used to create a voice model for an internal customer experience (CX) AI application.
- Applicants should only apply if they are comfortable with voice cloning for this specific internal use case.
- Voice data will not be sold, licensed, or reused for unrelated commercial products or datasets.
Why Join
- Contribute to the development of next-generation AI speech technologies.
- Apply your professional voice talent to innovative AI research.
- Work remotely with a flexible schedule.
- Participate in a high-impact project helping improve natural, human-like AI voice systems.
Equal Opportunity Statement
We are committed to providing equal opportunities to all qualified applicants without regard to legally protected characteristics. Reasonable accommodations are available upon request.