Advance the state of AI voice technology. Work on text-to-speech, voice cloning, and speech synthesis.
What you'll do:
- Research and implement novel TTS architectures
- Improve voice quality, naturalness, and emotion
- Develop voice cloning and adaptation techniques
- Publish research and contribute to the field
Requirements
- PhD in Speech Processing, ML, or related field
- Experience with speech synthesis and TTS systems
- Strong background in deep learning for audio
- Publications in speech/audio venues (ICASSP, Interspeech)
Required Skills
PythonPyTorchTensorFlowCUDA
About ElevenLabs
The most realistic AI voice platform. Text-to-speech, voice cloning, and audio AI.