mcp · handle speechcraft
mcp_speak · job 76%VoxCPM Audio MCP · job 75%Whisper MCP · job 78%dsh-fish-audio · job 71%VoiceOps Platform · job 80%WB Voice Intent MCP · job 77%mcp_tts_voicevox · job 76%Voice-MCP · job 74%PI TTS Pack · job 72%DSPark Studio · job 76%VOICEVOX Avatar Studio · job 76%mcp-voice · job 79%ElevenLabs MCP Server · job 75%VoiceSmith · job 75%loop-tts · job 71%Speech-MCP · job 79%telnyx · job 73%Audio Studio MCP · job 77%VoiceLab MCP Server · job 75%VoiceLayer · job 74%Sofa Coder · job 78%ChatGPT Voice MCP · job 72%audio-mcp · job 80%MCP Agent Chatterbox · job 74%Dottie Talk · job 75%Utterlane Live · job 82%Talkies · job 73%ThotStream Lite · job 76%AudioToText MCP · job 74%babelscribe · job 73%SuperClonica · job 71%voiceconsole · job 79%语伴（Talk） · job 76%Whisper Studio · job 72%MCP TTS Say · job 71%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.
Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.
This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series