This plugin brings advanced text-to-speech capabilities to Obsidian, leveraging the power of OpenAI's TTS API to provide high-quality speech synthesis directly within your notes. Whether you're looking to enhance your productivity or make your notes more accessible, this plugin offers a seamless integration with Obsidian.
- OpenAI Speech API: Utilize the advanced audio capabilities of OpenAI's models for high-quality text-to-speech synthesis.
- Customizable Settings: Tailor the plugin's behavior to your needs with customizable settings, including API key, API URL, model selection, and language preference.
- Install the Plugin: Search for "Speech Synthesizer" in Obsidian's community plugins browser and install it.
- Configure API Key: Obtain an OpenAI API key here and input it in the plugin's settings to activate the plugin's capabilities.
- Speech Tuning: Shape the tone of your voice synthesizer to fit your workflow, including 6 voices, speed, and volume settings (more to come).
- API Key: Your OpenAI API key. Required for accessing the OpenAI TTS API.
- API URL: The endpoint for TTS API requests. Default is set for optimal performance.
- Model: Selects the model for speech synthesis. Default model (tts-1) is recommended. tts-1-hd available for high-fidelity audio. Updates coming soon
Contributions to the Speech Synthesizer plug-in are welcome. Whether it's through submitting bug reports, suggesting new features, or contributing to the code, all input is welcome. Check out the GitHub repository for more information on how to get involved, including submitting issues & PRs.
For a detailed list of changes in each version, please refer to the CHANGELOG.md file.
This project is licensed under the MIT License. See the LICENSE file for more details.
- Special Thanks: Nik Danilov for the original Whisper plugin, which inspired this Speech Synthesizer plugin.