MCP Tools DirectoryAbout this integration
Natural voice conversations for AI assistants - STT/TTS via MCP
- Transport
- stdio
- Authentication
- none
- Initial setup
- none
- Runtime
- unattended
- Evidence
- documented
- Version
- 8.12.0
- Package
- voice-mode
- Last compatibility test
- Not independently tested
Connect your agent
voice-modePublisher README and source manifest were reviewed. The package, microphone/audio path, local services, optional cloud services, and MCP connection were not executed or independently security-audited.
Capabilities: Provide spoken conversations for MCP-capable assistants, Use local speech-to-text and text-to-speech services, Optionally use cloud voice services with user-supplied credentials
Connected profiles
Additional details
dev.voicemode/voicemode
Source ↗ · Checked 2026-09-178.12.0
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17voice-mode
Source ↗ · Checked 2026-09-19unspecified
Source ↗ · Checked 2026-09-19The documented launcher starts a local stdio server when VOICEMODE_MCP_URL is unset and can bridge to a configured remote server when it is set; this eligibility upgrade preserves the existing local stdio connection.
Source ↗ · Checked 2026-09-19The documented local/offline path does not require an OpenAI API key; the README describes that key only as an optional fallback for cloud services.
Source ↗ · Checked 2026-09-19Claude Code is configured to launch the voice-mode package's voicemode-mcp-launcher through uvx; the manifest maps that launcher to voice_mode.mcp_launcher:main.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19