speak-tts

Real-time text-to-speech with voice cloning on Apple Silicon, entirely on-device. Give your agent the ability to speak to you real-time. Local text-to-speech, voice cloning, and audio generation on Apple Silicon. Local TTS with voice cloning on Apple Silicon. Always create custom directories first: Voice cloning generates speech that matches your vocal characteristics (pitch, tone, cadence) from a short recording. Using QuickTime: Using sox (command line): Voice samples MUST be: WAV, 24000 Hz, mono, 10-30 seconds. Path requirements: When --voice is omitted, a built-in default voice is used: Tags produce audible effects (actual sounds), not spoken words: NOT supported: [pause] , [whisper] (ignored) For pauses: Use punctuation: "Wait... let me think." When using --auto-chunk with batch processing: You don't need to manually concatenate chunks — only concatenate final chapter files. Critical for correct concatenation order: Why: Shell glob expansion sorts alphabetically.