TTSBox0

TTSBox is a browser-based AI audio toolkit offering free text-to-speech and speech-to-text capabilities. It leverages WebGPU and WebAssembly for local processing, ensuring user data stays on the device. Key features include:

• Text to Speech: Convert text into spoken audio using built-in voices or authorized voice cloning.
• Speech to Text: Transcribe audio files or recordings into editable text.
• Voice Cloning: Optional feature within text-to-speech to clone voices with permission.
• Privacy: No server uploads; runs entirely in the browser after initial model download.
• No Signup: No account or API keys required.
• Output: WAV audio and text transcripts.

Use cases include narration drafts, accessibility experiments, transcription of personal notes, and testing voice styles. Recommended for users who prioritize privacy and quick, local AI audio processing.