Procedural Voice Designer

About this task

Role:
Create high-quality synthetic voice performances for games and digital entertainment using modern Text-to-Speech and Speech-to-Speech platforms. The role combines creative direction, technical expertise, voice design, prompt engineering, editing and quality control within an audio production workflow.

Responsibilities:
- Design expressive AI-generated voice performances for games and interactive media.
- Develop voice briefs, character profiles, vocal direction and prompting strategies for voice generation.
- Interpret scripts and narrative context so performances match character personality, emotion and delivery style.
- Experiment with tone, pacing, narration techniques, emotional tags and prompt structures to improve performance quality.
- Collaborate with audio directors to refine performances through multiple iterations.
- Generate voice content using Text-to-Speech and Speech-to-Speech technologies.
- Select suitable synthetic speech platforms and voices based on project requirements.
- Build and maintain internal voice libraries and voice databases.
- Produce multiple performance variations for creative review where required.
- Support multilingual voice generation across numerous languages.
- Contribute to best practices and scalable AI voice production workflows.
- Work with production, localization and QA teams to optimize delivery pipelines.
- Help evaluate new procedural voice platforms, technologies and production techniques.
- Edit, clean and master generated dialogue using professional audio software.

Requirements:
- Experience in voice design, audio production, dialogue production, sound design or a related creative audio discipline.
- Understanding of synthetic voice tools, TTS/STS workflows or prompt-based voice generation.
- Strong ear for performance quality, emotion, pacing, clarity and character consistency.
- Ability to collaborate with directors, narrative designers, production, localization, QA and clients.