Speech Synthesis
Default cheap Qwen (Bailian), optional MiniMax. Voice cloning supported. Sign-in required; charged on success.
Please sign in.
In WeChat, open this page in your system browser to download the audio file.
Provider
Model
Voice
Single select — pick one voice for synthesis (not multi-select, not a prompt).
0 / 5000
1.0
Synthesizing…
Voice cloning
Upload mp3 / m4a / wav, 10s–5min, max 15MB. Preview charges TTS only; clone fee is charged on first synthesis.