Google Cloud Text-to-Speech

Convert text into lifelike, synthetic speech using an API powered by Google's DeepMind AI and advanced neural networks.

Google Cloud Text-to-Speech delivers high-fidelity, humanlike audio, leveraging DeepMind's speech synthesis expertise and models like Gemini-TTS and Chirp 3. The service offers a massive selection: 380+ voices across 75+ languages and variants, including key global languages (e.g., Mandarin, Hindi, Spanish). Developers gain granular control over output via Speech Synthesis Markup Language (SSML) and natural-language prompts, allowing precise adjustments to pitch, speed, and emotional expression. This technology is designed to improve customer interactions, power voice user interfaces, and create custom, brand-specific voices.

https://cloud.google.com/text-to-speech