tts

You can convert text to speech locally by running the tts CLI, which transforms written text into audible speech for hands-free consumption without relying on cloud APIs. It supports streaming playback, voice selection, and file input for batch processing.

Yes, batch processing text to audio is supported by passing file input to the local tts CLI. This allows you to automate audio generation from text files or prompts within scripts and save the results directly to an audio file.

Local text-to-speech generation supports selecting different voices and languages through CLI flags. You can also adjust the model size to balance audio quality and processing speed according to your local environment's capabilities.

The best way to stream audio during text-to-speech generation is using the streaming control flag in the local tts CLI. This enables real-time audio playback, allowing you to hear speech as it generates rather than waiting for the entire file to process.

No, an internet connection is not required because the text-to-speech generation uses local inference. By running models locally, you can perform voice cloning and audio generation entirely offline within your local environment.