personaplex_
1 MCP server offers this tool
What it usually takes
custom_voice– in 1 of 1listen_after– in 1 of 1persona– in 1 of 1seed– in 1 of 1temp_audio– in 1 of 1temp_text– in 1 of 1user_audio– in 1 of 1voice– 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? |
|---|---|---|
PersonaPlex co.huggingface.crawl54/personaplex Have PersonaPlex answer a recorded user turn in a chosen persona and voice. PersonaPlex is a full-duplex speech-to-speech model: it listens to the user's audio stream frame by frame and speaks at the same time, so it can backchannel, interrupt, and take turns naturally. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: The agent's audio track, a stereo conversation mix (user left, agent right), and the agent's transcript. | custom_voice,listen_after,persona,seed,temp_audio,temp_text,user_audio,voice | Not stated |