About this role
Join a pioneering AI research lab in developing advanced text-to-speech (TTS) systems that produce natural and expressive human-like voices. This role invites USA-based voice actors with native Southern American English accents to provide high-quality voice recordings essential for training and evaluating innovative speech models. Ideal candidates will have a background in voice acting, narration, or broadcasting and will be able to deliver consistent and expressive audio across various scripts.
Your voice recordings will be used exclusively for the client''s internal CX AI Agent and will not be sold, licensed, or reused for any other purpose.
Key Responsibilities- Record high-quality voice samples across diverse scripts, including conversational, narrative, and instructional formats.
- Deliver clear, natural, and expressive speech with strong control over tone, pacing, and pronunciation.
- Maintain consistency in voice, accent, and delivery across recording sessions.
- Adhere to detailed recording guidelines regarding environment, microphone setup, and file formatting.
- Perform multiple takes with variations in emotion, emphasis, and style as needed.
- Native Southern American English speaker currently residing in the United States, with an authentic Southern US accent.
- Proven experience in voice acting, dubbing, narration, podcasting, or broadcasting.
- Access to a professional or near-professional recording setup, including a quality microphone, quiet environment, and pop filter.
- Strong command of intonation, diction, and emotional range.
- Ability to follow scripts precisely while maintaining a natural delivery.
- Reliable availability for 5, 10 hours per week throughout the project duration, which is expected to last 1, 2 weeks.
- Your voice may be cloned for the client''s CX AI Agent, so please apply only if you are comfortable with voice cloning. Your recordings will not be sold or reused outside of this specific use case.
- Experience recording for TTS, audiobooks, IVR systems, or AI voice datasets.
- Familiarity with audio editing tools such as Audacity, Adobe Audition, or Reaper.
- Ability to deliver multiple vocal styles, including conversational, corporate, energetic, and calm.