higgs_audio_v2_text_to_speech – 1 MCP server offers this tool
What it usually takes
max_completion_tokens– in 1 of 1ras_win_len– in 1 of 1ras_win_max_num_repeat– in 1 of 1reference_audio– in 1 of 1reference_text– in 1 of 1stop_strings– in 1 of 1system_prompt– in 1 of 1temperature– in 1 of 1text– in 1 of 1top_k– in 1 of 1top_p– in 1 of 1voice_preset– 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
| Server | Inputs | Read-only? |
|---|---|---|
Higgs Audio Demo co.huggingface.smola/higgs_audio_v2 Convert text to speech using HiggsAudioServeEngine. Returns: Tuple of (generated_text, (sample_rate, audio_data)) where audio_data is int16 numpy array | max_completion_tokens,ras_win_len,ras_win_max_num_repeat,reference_audio,reference_text,stop_strings,system_prompt,temperature,text,top_k,top_p,voice_preset | Not stated |