Skip to main content
Glama
Sign In
mac-voice-mcp

mac-voice-mcp

by jeet0007
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to mac-voice-mcp

No user-submitted related servers found.

    Related Servers

    • Raz

      Mateob6
      A
      license
      Not graded
      quality
      C
      maintenance
      Voice interface for Claude Code enabling hands-free, conversational interaction entirely on-device for Apple Silicon Macs. It provides push-to-talk transcription and automatic spoken responses via local AI models.
      MIT

    • Voice MCP

      shreyaskarnik
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables bidirectional voice interaction for Claude Code using local speech-to-text and text-to-speech models optimized for Apple Silicon. It provides tools to listen to user speech via microphone and speak responses aloud through system speakers.
      16
      Apache 2.0

    • Call Recorder MCP

      morganseznec
      A
      license
      A
      quality
      A
      maintenance
      Enables Claude to capture both sides of macOS calls and meetings from apps like WhatsApp, Teams, Zoom, and browsers as aligned microphone and system-audio tracks, then transcribe them locally with Whisper. Supports speaker separation, custom vocabulary, and importing existing audio or video files, with everything processed on-device so no audio leaves the Mac.
      10
      MIT

    • Voice Loop MCP

      theonlypal
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables hands-free voice conversations with Claude using real-time speech recognition and text-to-speech on macOS. Creates a self-sustaining conversation loop where Claude can autonomously listen, respond, and continue the interaction without keyboard input.
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.3/5.0

    Scored across 5 tools

    Disambiguation4/5

    Each tool has a distinct role: call manages the session, listen and say operate during a call, speak_and_listen handles a standalone spoken turn, and voice_setup handles installation. The main possible confusion is between say and speak_and_listen because both produce speech, but the descriptions clarify that say is call-only while speak_and_listen is for non-call use.

    Naming Consistency3/5

    The names are all lowercase and readable, but they mix conventions: bare verbs (call, listen, say), a noun-like setup name (voice_setup), and a compound verb phrase (speak_and_listen). There is no single predictable verb_noun or action pattern, though the set is small enough that the inconsistency does not make it chaotic.

    Tool Count5/5

    Five tools is well-scoped for a voice interaction server. Each tool has a clear role: setup, call lifecycle, in-call speaking/listening, and standalone speak-and-listen. No tool appears redundant or unnecessary.

    Completeness4/5

    The surface covers the core voice workflow: checking/installing dependencies, starting and ending calls, speaking, listening, and standalone spoken turns. Minor gaps exist around interrupting speech, muting during a call, or inspecting voice/session status, but these are not fatal for the stated purpose.

    Maintenance

    ActivityActive
    ResponsivenessUnresponsive

    Resources