A
licenseA
qualityB
maintenanceMCP server for audio transcription using local faster-whisper or OpenAI Whisper API, enabling multilingual transcription with optional GPT post-processing.
3
117 PyPI
MIT
Le Scribe Audio — Transcription Audio & Vidéo (FR)
Server Details
Official Le Scribe Audio MCP server: search, read, summarize & code French audio transcripts.
If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-03-26
- URL
- Repository
- zoulouzaza76/lescribeaudio-mcp
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
A4/5.0
Scored across 6 tools
Disambiguation5/5
Each tool has a clearly distinct purpose: listing, searching, retrieving text, retrieving summary, getting export URLs, and renaming a speaker label. The overlap between get_transcription_text and get_transcription_summary is minimal because one targets full diarized text and the other a structured synthesis. Search and list are also clearly separated by keyword-based lookup versus account enumeration.
Naming Consistency5/5
All tool names follow a consistent snake_case verb_noun pattern: get_*, list_*, search_*, rename_*. The convention is predictable and easy for an agent to parse.
Tool Count5/5
Six tools is well-scoped for a transcription retrieval and export service. Each tool covers a meaningful operation without obvious redundancy or missing core access paths.
Completeness4/5
The set covers listing, searching, reading text and summaries, exporting, and renaming speaker labels, which supports the main retrieval workflows. Minor gaps exist around creating/uploading transcriptions, deleting files, or generating a summary if one does not already exist, but agents can still accomplish most read/export tasks.
Available Tools
6 toolsget_export_urlsARead-onlyIdempotentInspect
Retourne le lien du lecteur interactif Studio et les URLs d'export disponibles (Word .docx 100 % modifiable, PDF, sous-titres .SRT / .VTT, texte brut .TXT, corpus IRaMuTeQ) pour un dossier.
Inputs: file_id (required).
get_transcription_summaryARead-onlyIdempotentInspect
Récupère la synthèse structurée (synthèse exécutive suivie du développement chrono-thématique) associée à une transcription si elle a été générée.
Inputs: file_id (required).
get_transcription_textARead-onlyIdempotentInspect
Récupère le texte intégral diarisé (par intervenant, avec timecodes optionnels [HH:MM:SS]) d'une transcription appartenant à l'utilisateur.
Inputs: file_id (required), max_chars, offset_chars, include_timecodes.
list_transcriptionsARead-onlyIdempotentInspect
Liste les transcriptions audio et vidéo du compte Le Scribe Audio authentifié (avec file_id, nom du fichier, durée, statut, date et présence d'une synthèse).
Inputs: limit, status.
rename_speaker_labelAIdempotentInspect
Renomme globalement l'étiquette d'un intervenant (diarisation) sur toutes ses prises de parole (ex: remplacer 'Intervenant 1' par 'Enquêté P1' ou 'M. Martin') et met à jour les futurs exports Word (.docx).
Inputs: file_id (required), new_speaker (required), old_speaker (required).
search_transcriptionsARead-onlyIdempotentInspect
Recherche un mot-clé, un thème ou un intervenant dans les titres, synthèses et textes déverrouillés des transcriptions de l'utilisateur, avec extraits horodatés.
Inputs: query (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
MCP server for RiverScript, an AI transcription platform - fetches transcripts shared via a link.
MCP server for structured access to Lenny Rachitsky podcast transcripts. For content creators.
Search, read, analyze and create HappyScribe transcripts and meeting notes from any MCP client
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
Related MCP Servers
- AlicenseAqualityDmaintenanceOfficial ElevenLabs MCP server for text-to-speech, voice cloning, audio transcription, and sound generation.24MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for audio transcription with speaker diarization. Transcribes MP3/WAV files using Faster-Whisper and pyannote.audio, outputs markdown with speaker labels, timestamps, summaries, and action items.1MIT
- AlicenseAqualityDmaintenanceOfficial MCP server for FormaCV, enabling AI-powered CV formatting, anonymization, tailoring, and ATS push-back from AI agents like Claude Desktop and Cursor.844 npm18MIT
Try in Browser
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
Glama MCP Gateway
Add one secure layer between your agents and this server.