Clone a voice in 30 seconds.
Synthesise for hours.
Zero-shot voice cloning on Apple Silicon. IndexTTS2 adds native MLX cloning with emotion, tempo, and pause controls; CosyVoice 3 covers transcript-conditioned multilingual cloning; Chatterbox Flash adds a CoreML T3 + S3Gen path with an MLX reference encoder. No fine-tuning, no per-character pricing, no audio ever leaving the device.
Five voice-cloning recipes.
Each recipe picks the synthesis engine that fits the product: IndexTTS2 for reference-only MLX cloning with style controls, CosyVoice 3 for transcript-conditioned multilingual zero-shot, Chatterbox Flash for CoreML Flash T3 cloning, Qwen3-TTS ICL when you only have audio, plus speaker embeddings and denoising around them.
Clone the author or a chosen voice once, render hours of consistent narration.
Keep a presenter's voice across translated tracks, in nine languages.
Two-to-four custom voices per scene via inline speaker tags.
Restore a familiar voice for users who can no longer speak naturally.
A single consistent narrator across an entire product line.