---
bezeichner: "io.github.JuhongPark/pronunciation"
art: "mcp_server"
slug: "io-github-juhongpark-pronunciation"
paketkoordinate: "pypi:mcp-server-pronunciation"
status: "aktiv"
homepage: "https://github.com/JuhongPark/mcp-server-pronunciation"
erhebungsstand: "2026-10-11T01:17:01.851Z"
namensraum: "io.github.JuhongPark"
registerseite: "https://tracevero.de/mcp/io-github-juhongpark-pronunciation"
abgerufen_am: "2026-10-11"
zugangsdaten_erforderlich: false
ausfuehrungsort: "lokal"
dateisystem_pfadargument: false
quelloffen_einsehbar: true
einsatzgebiet: "audio"
roh_beschreibung: "Local MCP voice coach with English pronunciation, grammar, and fluency feedback."
version: "0.3.0"
roh_umgebungsvariablen: "MCP_PRONUNCIATION_MODEL, HF_HUB_CACHE, MCP_PRONUNCIATION_PRELOAD, MCP_PRONUNCIATION_AUDIO_RETENTION, TORCH_HOME"
roh_geheime_pflichtvariablen: ""
roh_transportarten: "stdio"
roh_pfadargumente: ""
roh_repository_url: "https://github.com/JuhongPark/mcp-server-pronunciation"
roh_paketquellen: "pypi"
roh_geheime_pflichtkopfzeilen: ""
roh_pfad_umgebungsvariablen: ""
roh_remote_adressen: ""
roh_remote_hosts: ""
roh_statusmeldung: ""
roh_veroeffentlicht_am: "2026-05-03"
roh_aktualisiert_am: "2026-05-03"
roh_schemafassung: "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json"
roh_bereitstellungsform: "paket"
roh_repository_quelle: "github"
roh_repository_unterordner: ""
roh_paketbezeichner: "mcp-server-pronunciation"
roh_paketversionen: "0.3.0"
roh_laufzeithinweise: "uvx"
roh_umgebungsformate: ""
roh_umgebungsbeschreibungen: "HF_HUB_CACHE=Override Hugging Face Hub cache directory where Whisper weights are stored. · MCP_PRONUNCIATION_AUDIO_RETENTION=Temporary WAV retention policy. Use session to delete recordings when the server exits, or keep for manual inspection. · MCP_PRONUNCIATION_MODEL=faster-whisper model size. Default: base.en. Options: tiny.en, base.en, small.en, medium.en, large-v3, large-v3-turbo. · MCP_PRONUNCIATION_PRELOAD=Set to 0, false, no, or off to disable background Whisper model preload during registry inspection or Docker smoke tests. · TORCH_HOME=Override PyTorch cache directory for optional wav2vec2 forced-alignment weights."
roh_symbolformate: ""
roh_verbindungswege: "{\"packages\":[{\"registryType\":\"pypi\",\"identifier\":\"mcp-server-pronunciation\",\"version\":\"0.3.0\",\"runtimeHint\":\"uvx\",\"transport\":\"stdio\",\"environment\":[{\"name\":\"MCP_PRONUNCIATION_MODEL\",\"description\":\"faster-whisper model size. Default: base.en. Options: tiny.en, base.en, small.en, medium.en, large-v3, large-v3-turbo.\",\"required\":false,\"secret\":false},{\"name\":\"HF_HUB_CACHE\",\"description\":\"Override Hugging Face Hub cache directory where Whisper weights are stored.\",\"required\":false,\"secret\":false},{\"name\":\"MCP_PRONUNCIATION_PRELOAD\",\"description\":\"Set to 0, false, no, or off to disable background Whisper model preload during registry inspection or Docker smoke tests.\",\"required\":false,\"secret\":false},{\"name\":\"MCP_PRONUNCIATION_AUDIO_RETENTION\",\"description\":\"Temporary WAV retention policy. Use session to delete recordings when the server exits, or keep for manual inspection.\",\"required\":false,\"secret\":false},{\"name\":\"TORCH_HOME\",\"description\":\"Override PyTorch cache directory for optional wav2vec2 forced-alignment weights.\",\"required\":false,\"secret\":false}],\"additional_arguments_declared\":false}],\"remotes\":[]}"
---

# Pronunciation & Voice Coach

## Gemessene Werte

| Merkmal | Wert | Quelle | Erhoben am | Vertrauensgrad | Rohangabe |
| --- | --- | --- | --- | --- | --- |
| Pflicht-Geheimnisse deklariert | false | MCP-Register | 2026-08-06T13:57:41.838Z | abgeleitet | roh_geheime_pflichtvariablen: ; roh_geheime_pflichtkopfzeilen: |
| Ausführungsort | lokal | MCP-Register | 2026-08-06T13:57:41.838Z | abgeleitet | roh_transportarten: stdio |
| Pfadargument vorhanden | false | MCP-Register | 2026-08-06T13:57:41.838Z | abgeleitet | roh_pfadargumente: ; roh_pfad_umgebungsvariablen: |
| Repository-Adresse geführt | true | MCP-Register | 2026-08-06T13:57:41.838Z | abgeleitet | roh_repository_url: https://github.com/JuhongPark/mcp-server-pronunciation |
| Einsatzgebiet, aus der Anbieterbeschreibung abgeleitet | audio | MCP-Register | 2026-08-26T16:45:01.514Z | abgeleitet | roh_beschreibung: Local MCP voice coach with English pronunciation, grammar, and fluency feedback. |
| Beschreibung (Rohangabe) | Local MCP voice coach with English pronunciation, grammar, and fluency feedback. | MCP-Register | 2026-08-26T16:45:01.514Z | selbstauskunft |  |
| Deklarierte Version | 0.3.0 | MCP-Register | 2026-08-06T13:57:41.838Z | selbstauskunft |  |
| Umgebungsvariablen (Rohangabe) | MCP_PRONUNCIATION_MODEL, HF_HUB_CACHE, MCP_PRONUNCIATION_PRELOAD, MCP_PRONUNCIATION_AUDIO_RETENTION, TORCH_HOME | MCP-Register | 2026-08-06T13:57:41.838Z | selbstauskunft |  |
| Geheime Pflichtvariablen (Rohangabe) |  | MCP-Register | 2026-08-06T13:57:41.838Z | selbstauskunft |  |
| Transportarten (Rohangabe) | stdio | MCP-Register | 2026-08-06T13:57:41.838Z | selbstauskunft |  |
| Pfadargumente (Rohangabe) |  | MCP-Register | 2026-08-06T13:57:41.838Z | selbstauskunft |  |
| Repository (Rohangabe) | https://github.com/JuhongPark/mcp-server-pronunciation | MCP-Register | 2026-08-06T13:57:41.838Z | selbstauskunft |  |
| Paketquellen (Rohangabe) | pypi | MCP-Register | 2026-08-06T13:57:41.838Z | selbstauskunft |  |
| Geheime Pflichtkopfzeilen (Rohangabe) |  | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Pfad-Umgebungsvariablen (Rohangabe) |  | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Remote-Adressen (Rohangabe) |  | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Remote-Hosts (Rohangabe) |  | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Statusmeldung des Registers (Rohangabe) |  | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Im Register eingetragen am (Rohangabe) | 2026-05-03 | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Im Register geändert am (Rohangabe) | 2026-05-03 | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Schemafassung des Rohsatzes (Rohangabe) | https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Bereitstellungsform (Rohangabe) | paket | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Repository-Plattform (Rohangabe) | github | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Repository-Unterordner (Rohangabe) |  | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Paketbezeichner (Rohangabe) | mcp-server-pronunciation | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Paketversionen (Rohangabe) | 0.3.0 | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Laufzeithinweise (Rohangabe) | uvx | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Formate der Umgebungsvariablen (Rohangabe) |  | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Beschreibungen der Umgebungsvariablen (Rohangabe) | HF_HUB_CACHE=Override Hugging Face Hub cache directory where Whisper weights are stored. · MCP_PRONUNCIATION_AUDIO_RETENTION=Temporary WAV retention policy. Use session to delete recordings when the server exits, or keep for manual inspection. · MCP_PRONUNCIATION_MODEL=faster-whisper model size. Default: base.en. Options: tiny.en, base.en, small.en, medium.en, large-v3, large-v3-turbo. · MCP_PRONUNCIATION_PRELOAD=Set to 0, false, no, or off to disable background Whisper model preload during registry inspection or Docker smoke tests. · TORCH_HOME=Override PyTorch cache directory for optional wav2vec2 forced-alignment weights. | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Symbolformate (Rohangabe) |  | MCP-Register | 2026-08-16T01:17:01.420Z | selbstauskunft |  |
| Verbindungswege (Quellstruktur) | {"packages":[{"registryType":"pypi","identifier":"mcp-server-pronunciation","version":"0.3.0","runtimeHint":"uvx","transport":"stdio","environment":[{"name":"MCP_PRONUNCIATION_MODEL","description":"faster-whisper model size. Default: base.en. Options: tiny.en, base.en, small.en, medium.en, large-v3, large-v3-turbo.","required":false,"secret":false},{"name":"HF_HUB_CACHE","description":"Override Hugging Face Hub cache directory where Whisper weights are stored.","required":false,"secret":false},{"name":"MCP_PRONUNCIATION_PRELOAD","description":"Set to 0, false, no, or off to disable background Whisper model preload during registry inspection or Docker smoke tests.","required":false,"secret":false},{"name":"MCP_PRONUNCIATION_AUDIO_RETENTION","description":"Temporary WAV retention policy. Use session to delete recordings when the server exits, or keep for manual inspection.","required":false,"secret":false},{"name":"TORCH_HOME","description":"Override PyTorch cache directory for optional wav2vec2 forced-alignment weights.","required":false,"secret":false}],"additional_arguments_declared":false}],"remotes":[]} | MCP-Register | 2026-09-08T01:17:01.649Z | selbstauskunft |  |

## Verweise

- Namensraum: [[namensraum/io-github-juhongpark|io.github.JuhongPark]]

---

- Registerseite: <https://tracevero.de/mcp/io-github-juhongpark-pronunciation>
- Abgerufen am: 2026-10-11