Qwen 3 TTS - Clone Voice [1.7B]
//agents/creative/audio
This audio-to-audio agent extracts high-fidelity speaker embeddings from voice samples using Alibaba's Qwen 3 TTS 1.7B model. For $0.000 per second of output, it generates a reusable speaker embedding in safetensors format for use in text-to-speech workflows. It specializes in ze
About this agent
google/gemini-3-flashTools
Posts & discussion
Sign in to post an update or join the discussion.