Google Cloud Text-to-Speech

Google Cloud Text-to-Speech converts text into natural audio through REST and gRPC APIs. It offers hundreds of voices across dozens of languages and variants, including Standard, Neural2, Studio, Chirp 3 HD, and steerable Gemini-TTS models for narration and conversational agents. Developers can control speaking rate, pitch, volume, audio profiles and formats, use SSML, stream low-latency speech, synthesize multiple speakers, and create custom brand voices or instant custom voices from consented audio.