This lets Claude synthesize speech using Chanjing's TTS API with voice cloning from a reference audio file you provide via public URL. The flow is async: you submit a reference audio URL (mp3, wav, or m4a), wait for the voice profile to build, then generate speech from text using that cloned voice. Supports bilingual Chinese and English with adjustable speech rate and sentence timestamps. You'll need Chanjing credentials (app_id and secret_key), and the skill handles token refresh automatically by writing back to the same credentials file. The reference audio gets fetched by Chanjing's servers, so it needs to be publicly accessible. Polling can take a few minutes while the voice processes, but no local ffmpeg required since everything happens server-side.
npx skills add https://github.com/chanjing-ai/chan-skills --skill chanjing-tts-voice-clone