qwen3_tts_customvoice_compare_speech

1 MCP server offers this tool

What it usually takes

  • do_sample – in 1 of 1
  • instruct_a – in 1 of 1
  • instruct_b – in 1 of 1
  • language_a – in 1 of 1
  • language_b – in 1 of 1
  • max_new_tokens – in 1 of 1
  • randomize_seed – in 1 of 1
  • repetition_penalty – in 1 of 1
  • seed – in 1 of 1
  • speaker_a – in 1 of 1
  • speaker_b – in 1 of 1
  • temperature – in 1 of 1

No server marks it as only reading: treat it as able to change data.

From each publisher's own tool list. We never call a tool.

Servers

ServerInputsRead-only?
Qwen3-TTS CustomVoice Lab co.huggingface.henrybit/qwen3-tts-customvoice Generate two CustomVoice variants of the same text for A/B listening.do_sample,instruct_a,instruct_b,language_a,language_b,max_new_tokens,randomize_seed,repetition_penalty,seed,speaker_a,speaker_b,temperature,text,top_k,top_pNot stated