Soundwaver
AI text-to-speech platform with director-mode emotion control, 30-second voice cloning and custom voice design. Free to start, paid from $6/mo.
• Copy the embed code to showcase this product on your website
• Share on X to spread the word about this amazing tool
Soundwaver is an AI text-to-speech platform built on the MiMo-V2.5-TTS model, designed for Chinese-language content creators. Director Mode lets you control delivery with plain-language instructions (e.g. "excited, slightly fast, with a smile") instead of tweaking endless sliders. Clone a voice from a 30-second sample, or design a brand-new voice with WaveMind simply by describing it in words. A community voice library lets creators discover and use voices shared by others. The free plan includes 1,000 credits (approx. 50,000 Chinese characters) with 1 voice slot and 1 clone slot; paid plans start at $6/mo (7,200 credits) with up to 4,000 characters per generation — chapter-length text for audiobooks. Ideal for short-video narration, audiobooks and e-learning. Bilingual Chinese/English interface, secure checkout via Stripe.