# Test-to-Speech ### Overview The KidJig API provides access to advanced Text-to-Speech (TTS) models that convert written text into natural-sounding speech. These powerful models enable you to create voice content for a wide range of applications, from accessibility features to interactive voice responses. ### Key Features * **Natural-Sounding Voices**: Our TTS models produce human-like speech with natural intonation and rhythm * **Multiple Voice Options**: Choose from a variety of voices with different characteristics, accents, and speaking styles * **Fast Processing**: Experience quick conversion of text to speech, ensuring a responsive user experience * **Multiple Providers**: Access TTS capabilities from leading providers including ElevenLabs, OpenAI Whisper, and Sarvam.ai * **Cloud Storage**: All generated audio files are automatically stored in the cloud for easy access and distribution ### Use Cases With our API, you can leverage TTS models for various applications, including: * **Accessibility**: Make content accessible to users with visual impairments or reading difficulties * **Content Creation**: Generate voiceovers for videos, podcasts, or audiobooks * **Interactive Voice Response**: Build voice-based interfaces for applications and services * **Language Learning**: Create pronunciation examples for language learning applications * **Gaming**: Add voice dialogue to gaming characters and NPCs ### Supported Providers We currently support the following TTS providers: * **ElevenLabs**: Known for highly realistic and expressive voices * **OpenAI Whisper**: Offers clear and natural-sounding speech synthesis * **Sarvam.ai**: Provides high-quality voices with support for multiple languages and accents ### Explore More Dive into the specific sections of our documentation to learn more about each provider's capabilities, available voices, request and response formats, and best practices for integration. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://kidjig.gitbook.io/kidjig-docs/api-provider/voice-speech-models/test-to-speech.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.