Director, Text-to-Speech Synthesis Research

About the role

Deepgram is seeking a Director of Research to lead the end-to-end Text-to-Speech program, including research strategy, technical direction, and model deployment. This hands-on leadership role involves shaping architectures, training strategies, and evaluation frameworks while building and mentoring a high-performing team of researchers. The successful candidate will advance the state of the art in speech generation and ensure these innovations translate into measurable production gains.

Responsibilities

• Own the TTS research and model roadmap, deciding on technical directions and evaluating the viability of research approaches.
• Drive advancements in neural audio modeling, prosody, expressiveness, controllability, and inference performance.
• Maintain deep technical involvement by reviewing research, designing experiments, and diagnosing model failures.
• Develop evaluation and benchmarking systems that combine automated metrics with human perceptual assessment.
• Lead and mentor a team of individual contributors and tech lead managers, setting high technical standards.
• Partner with engineering and product leadership to ensure research outputs are ready for production deployment.

Required skills

• Text-to-Speech
• Speech generation
• Audio generative modeling
• Neural models
• Research leadership
• AI

Nice to have

• Production-scale deployment
• Research organization scaling
• Evaluation systems
• Multilingual speech generation
• Voice cloning
• Controllable generation

About the Company

Deepgram is a leading platform in the Voice AI economy, providing real-time APIs for speech-to-text and text-to-speech. The company supports over 200,000 developers and 1,300 organizations with voice-native foundation models that offer high accuracy and low latency.