Speech ML Engineer

About the Role

ElevenLabs is seeking a Speech ML Engineer to advance the state of the art in voice synthesis and cloning. You will develop neural TTS models, work on voice conversion techniques, and build systems for ultra-realistic speech generation.

Requirements

• 4+ years of experience in speech/audio ML
• Expertise in neural TTS (Tacotron, VITS, etc.)
• Strong proficiency in Python and PyTorch
• Experience with audio processing and signal analysis
• Understanding of speech synthesis evaluation metrics

Nice to Have

• Experience with voice cloning or voice conversion
• Background in music information retrieval
• Experience with codec-based speech models
• Multilingual speech synthesis experience

Benefits

Skills

Related Jobs