MCP Tools DirectoryAbout this integration
Transcribe audio locally with faster-whisper or through the OpenAI Whisper API.
- Transport
- stdio
- Authentication
- unknown
- Initial setup
- unknown
- Runtime
- unattended
- Evidence
- documented
- Version
- 1.1.2
- Package
- whisper-transcribe-mcp
- Last compatibility test
- Not independently tested
Connect your agent
whisper-transcribe-mcpPublisher README and package manifest reviewed. The package, local models, audio files, and OpenAI service were not executed; transcription accuracy and fallback behavior were not independently tested.
Capabilities: audio transcription, local speech recognition, cloud speech recognition, model listing
Connected profiles
Additional details
io.github.ZahiriNatZuke/whisper-transcribe-mcp
Source ↗ · Checked 2026-09-171.1.2
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17whisper-transcribe-mcp
Source ↗ · Checked 2026-09-201.1.2
Source ↗ · Checked 2026-09-20Runs as a host-launched stdio MCP server. With the all extra, backend selection happens at startup and documented failures of the OpenAI path fall back to the local backend.
Source ↗ · Checked 2026-09-20Authentication is backend-dependent: the local backend requires no service credential, while the OpenAI backend requires OPENAI_API_KEY.
Source ↗ · Checked 2026-09-20The pinned MCP configurations launch uvx with an explicit package extra such as whisper-transcribe-mcp[local], [openai], or [all].
Source ↗ · Checked 2026-09-20Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-20