Google Text-to-Speech

Synthesize lifelike audio using Google's AI: choose from 380+ WaveNet and Neural2 voices across 75+ languages, customizing with SSML for precise pitch and speed.

Google Cloud Text-to-Speech (TTS) delivers high-fidelity, humanlike audio, leveraging DeepMind's speech synthesis and new models like Gemini-TTS. You get immediate access to over 380 voices across 75+ languages, including Mandarin and Spanish variants. Use the API to generate voice for virtual assistants, e-learning platforms, or IVR systems, controlling delivery with SSML (Speech Synthesis Markup Language) for precise pitch and speaking rate adjustments. Start testing now: the service includes a free tier of up to 4 million characters monthly.

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