About
Speech.sh is a command-line tool designed for text-to-speech conversion, leveraging the power of OpenAI's API. It offers a straightforward way to vocalize text, especially useful in situations where vocal communication is impaired. With features like multiple voice options, adjustable speech speed, caching to avoid redundant API calls, and robust retry mechanisms, speech.sh provides a flexible and reliable solution for converting text into audible speech.
Key Features
- Converts text to speech with OpenAI API
- Includes a retry mechanism for handling network issues
- Adjustable speech speed (0.25 to 4.0)
- Automatic caching to prevent duplicate API calls
- Offers multiple voice options (onyx, alloy, echo, fable, nova, shimmer)
- 1 GitHub stars
Use Cases
- Reading text aloud when the user is unable to speak.
- Integrating text-to-speech functionality into automated scripts.
- Enabling AI assistants with speech capabilities.
