Editor Speech (TTS)
Last updated
Last updated
EditorTTS (Text-To-Speech) transforms written text into spoken words, leveraging advanced voice synthesis technology. This tool is instrumental in creating dynamic voiceovers, dialogues, and narrative content directly within the Unity Editor.
Open EditorTTS through Tools > Glitch9 > OpenAI > EditorTTS in the Unity Editor. This action will launch the dedicated window for EditorTTS, where you can start converting your text into speech.
Prompt Field: Type the text you wish to convert into speech in the provided input field.
Voice Selection: Choose a voice that best fits your project's tone and character needs from the available options.
Customizing Speech Parameters: Adjust settings such as speech speed to fine-tune the audio output according to your preferences.
Click the "Generate Speech" button after setting your prompt and preferences. EditorTTS will then process your request and generate an audio clip that you can preview, stop, and manage within the EditorTTS window.
Narration and Voiceovers: Generate voiceovers for trailers, in-game narratives, or instructional content.
Dynamic Dialogues: Create spoken dialogue for characters, enhancing the immersion and interaction within games.
Accessibility Features: Improve accessibility by providing spoken versions of text, aiding those with visual impairments.
Clear and Concise Prompts: Ensure your text is clear and free of ambiguities to generate coherent speech.
Experiment with Voices: Try different voices to find the perfect match for your characters or content.
Consider the Context: Adjust the speech speed and tone based on the context in which the speech will be used.
Playback Controls: Use the play and stop buttons to preview the generated speech directly within the EditorTTS window.
Session History: Access previously generated speech clips from the session history for easy review and reuse.
Review and Edit: Listen to the generated audio and make necessary adjustments to the text for better results.
API Usage Management: Be mindful of your API usage to ensure efficient use of resources and adherence to rate limits.
Secure Storage: Keep the generated speech files in a secure location, especially if they contain sensitive or proprietary information.
