Speech synthesis, avatar video, and lip sync models for character systems.
Conversational text-to-speech with realtime voice direction and audio-aware delivery
Promptable full-song generation with vocals, lyrics, BPM and key control
High-quality text-to-speech with expressive, natural voice synthesis
Lip-synced talking video from one portrait and an audio track or script, up to 3 minutes and 4K
Cognitive avatar video from image, audio, and text
High fidelity avatar video generation with smoother motion and quality
Full-scene lip synchronization with global face understanding and obstruction handling
High-resolution diffusion-based lip-sync editing up to 4K
Zero-shot audio-driven lip synchronization for video
How to write LLM system prompts that produce text TTS-2 can synthesize naturally, with normalization, filler words, and emphasis cues handled before the audio call.
How to use natural-language steering tags to control emotion, pacing, volume, and vocal style in TTS-2 speech output.