Skip to content

History of Talkthrough

io.github.korovin-aa97/talkthrough-mcp · Registry status: active

Report data on this entry

Every published change to this entry, most recent first.

Changes
2026-09-28Declared version: 0.4.1 → 0.4.2
2026-09-28Last changed in the registry (raw): 2026-09-06 → 2026-09-27
2026-09-28First listed in the registry (raw): 2026-09-06 → 2026-09-27
2026-09-28Connection paths (source structure): {"packages":[{"registryType":"pypi","identifier":"talkthrough-mcp","version":"0.4.1","runtimeHint":"uvx","transport":"stdio","environment":[{"name":"TALKTHROUGH_WHISPER_MODEL","description":"Whisper model (tiny|base|small|medium|large-v3|large-v3-turbo). Default: small. Use large-v3-turbo for non-English narration; the process_media `model` param overrides per call.","required":false,"secret":false},{"name":"TALKTHROUGH_OCR","description":"Set to 'off' to disable OCR of keyframes. Default: on.","required":false,"secret":false},{"name":"TALKTHROUGH_OCR_LANG","description":"Recognition script for on-screen text: a language code (ru, ja, ko, ar, hi, ...) or a RapidOCR pack name (eslav, cyrillic, ...). Default: Latin+Chinese.","required":false,"secret":false},{"name":"TALKTHROUGH_HOME","description":"Job store root. Default: ~/.talkthrough","required":false,"secret":false},{"name":"TALKTHROUGH_MAX_DOWNLOAD_BYTES","description":"Hard cap for one process_url download. Default: 2147483648 (2 GiB).","required":false,"secret":false}],"additional_arguments_declared":false}],"remotes":[]} → {"packages":[{"registryType":"pypi","identifier":"talkthrough-mcp","version":"0.4.2","runtimeHint":"uvx","transport":"stdio","environment":[{"name":"TALKTHROUGH_WHISPER_MODEL","description":"Whisper model (tiny|base|small|medium|large-v3|large-v3-turbo). Default: small. Use large-v3-turbo for non-English narration; the process_media `model` param overrides per call.","required":false,"secret":false},{"name":"TALKTHROUGH_OCR","description":"Set to 'off' to disable OCR of keyframes. Default: on.","required":false,"secret":false},{"name":"TALKTHROUGH_OCR_LANG","description":"Recognition script for on-screen text: a language code (ru, ja, ko, ar, hi, ...) or a RapidOCR pack name (eslav, cyrillic, ...). Default: Latin+Chinese.","required":false,"secret":false},{"name":"TALKTHROUGH_HOME","description":"Job store root. Default: ~/.talkthrough","required":false,"secret":false},{"name":"TALKTHROUGH_MAX_DOWNLOAD_BYTES","description":"Hard cap for one process_url download. Default: 2147483648 (2 GiB).","required":false,"secret":false}],"additional_arguments_declared":false}],"remotes":[]}
2026-09-28Package versions (raw): 0.4.1 → 0.4.2
2026-09-08Connection paths (source structure): – → {"packages":[{"registryType":"pypi","identifier":"talkthrough-mcp","version":"0.4.1","runtimeHint":"uvx","transport":"stdio","environment":[{"name":"TALKTHROUGH_WHISPER_MODEL","description":"Whisper model (tiny|base|small|medium|large-v3|large-v3-turbo). Default: small. Use large-v3-turbo for non-English narration; the process_media `model` param overrides per call.","required":false,"secret":false},{"name":"TALKTHROUGH_OCR","description":"Set to 'off' to disable OCR of keyframes. Default: on.","required":false,"secret":false},{"name":"TALKTHROUGH_OCR_LANG","description":"Recognition script for on-screen text: a language code (ru, ja, ko, ar, hi, ...) or a RapidOCR pack name (eslav, cyrillic, ...). Default: Latin+Chinese.","required":false,"secret":false},{"name":"TALKTHROUGH_HOME","description":"Job store root. Default: ~/.talkthrough","required":false,"secret":false},{"name":"TALKTHROUGH_MAX_DOWNLOAD_BYTES","description":"Hard cap for one process_url download. Default: 2147483648 (2 GiB).","required":false,"secret":false}],"additional_arguments_declared":false}],"remotes":[]}
2026-09-07Declared version: 0.4.0 → 0.4.1
2026-09-07Last changed in the registry (raw): 2026-09-05 → 2026-09-06
2026-09-07First listed in the registry (raw): 2026-09-05 → 2026-09-06
2026-09-07Package versions (raw): 0.4.0 → 0.4.1
2026-09-06Declared version: 0.3.2 → 0.4.0
2026-09-06Field of use, derived from the vendor description: Text recognition → Text recognition, Video
2026-09-06Description (raw): Local MCP server: screen recordings into transcript, exact frames, OCR, wall-clock evidence. → Local MCP server: recordings or public video URLs into transcript, frames, OCR, wall-clock evidence.
2026-09-06Last changed in the registry (raw): 2026-09-03 → 2026-09-05
2026-09-06First listed in the registry (raw): 2026-09-03 → 2026-09-05
2026-09-06Schema version of the raw record (raw): https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json → https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json
2026-09-06Environment variable descriptions (raw): TALKTHROUGH_HOME=Job store root. Default: ~/.talkthrough · TALKTHROUGH_OCR=Set to 'off' to disable OCR of keyframes. Default: on. · TALKTHROUGH_OCR_LANG=Recognition script for on-screen text: a language code (ru, ja, ko, ar, hi, ...) or a RapidOCR pack name (eslav, cyrillic, ...). Default: Latin+Chinese. · TALKTHROUGH_WHISPER_MODEL=Whisper model (tiny|base|small|medium|large-v3|large-v3-turbo). Default: small. Use large-v3-turbo for non-English narration; the process_media `model` param overrides per call. → TALKTHROUGH_HOME=Job store root. Default: ~/.talkthrough · TALKTHROUGH_MAX_DOWNLOAD_BYTES=Hard cap for one process_url download. Default: 2147483648 (2 GiB). · TALKTHROUGH_OCR=Set to 'off' to disable OCR of keyframes. Default: on. · TALKTHROUGH_OCR_LANG=Recognition script for on-screen text: a language code (ru, ja, ko, ar, hi, ...) or a RapidOCR pack name (eslav, cyrillic, ...). Default: Latin+Chinese. · TALKTHROUGH_WHISPER_MODEL=Whisper model (tiny|base|small|medium|large-v3|large-v3-turbo). Default: small. Use large-v3-turbo for non-English narration; the process_media `model` param overrides per call.
2026-09-06Package versions (raw): 0.3.2 → 0.4.0
2026-09-06Environment variables (raw): TALKTHROUGH_WHISPER_MODEL, TALKTHROUGH_OCR, TALKTHROUGH_OCR_LANG, TALKTHROUGH_HOME → TALKTHROUGH_WHISPER_MODEL, TALKTHROUGH_OCR, TALKTHROUGH_OCR_LANG, TALKTHROUGH_HOME, TALKTHROUGH_MAX_DOWNLOAD_BYTES
2026-09-06Name: io.github.korovin-aa97/talkthrough-mcp → Talkthrough
2026-09-04Declared version: 0.3.1 → 0.3.2
2026-09-04Last changed in the registry (raw): 2026-09-02 → 2026-09-03
2026-09-04First listed in the registry (raw): 2026-09-02 → 2026-09-03
2026-09-04Package versions (raw): 0.3.1 → 0.3.2
2026-09-03Declared version: 0.3.0 → 0.3.1
2026-09-03Last changed in the registry (raw): 2026-08-29 → 2026-09-02
2026-09-03First listed in the registry (raw): 2026-08-29 → 2026-09-02
2026-09-03Package versions (raw): 0.3.0 → 0.3.1
2026-08-30Declared version: 0.2.6 → 0.3.0
2026-08-30Last changed in the registry (raw): 2026-08-10 → 2026-08-29
2026-08-30First listed in the registry (raw): 2026-08-10 → 2026-08-29
2026-08-30Package versions (raw): 0.2.6 → 0.3.0
2026-08-26Field of use, derived from the vendor description: – → Text recognition
2026-08-26Description (raw): – → Local MCP server: screen recordings into transcript, exact frames, OCR, wall-clock evidence.
2026-08-16Last changed in the registry (raw): – → 2026-08-10
2026-08-16First listed in the registry (raw): – → 2026-08-10
2026-08-16Registry status message (raw): – → –
2026-08-16Schema version of the raw record (raw): – → https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json
2026-08-16Icon formats (raw): – → –
2026-08-16Environment variable descriptions (raw): – → TALKTHROUGH_HOME=Job store root. Default: ~/.talkthrough · TALKTHROUGH_OCR=Set to 'off' to disable OCR of keyframes. Default: on. · TALKTHROUGH_OCR_LANG=Recognition script for on-screen text: a language code (ru, ja, ko, ar, hi, ...) or a RapidOCR pack name (eslav, cyrillic, ...). Default: Latin+Chinese. · TALKTHROUGH_WHISPER_MODEL=Whisper model (tiny|base|small|medium|large-v3|large-v3-turbo). Default: small. Use large-v3-turbo for non-English narration; the process_media `model` param overrides per call.
2026-08-16Environment variable formats (raw): – → –
2026-08-16Delivery form (raw): – → package
2026-08-16Remote hosts (raw): – → –
2026-08-16Remote URLs (raw): – → –
2026-08-16Runtime hints (raw): – → uvx
2026-08-16Package versions (raw): – → 0.2.6
2026-08-16Package identifiers (raw): – → talkthrough-mcp
2026-08-16Repository subfolder (raw): – → –
2026-08-16Repository platform (raw): – → github
2026-08-16Path environment variables (raw): – → –

This view pages forward and states no total: individual rows are dropped only at output time when their evidence is missing. A counted total would be larger than what is shown.

tracevero · https://tracevero.com/mcp/io-github-korovin-aa97-talkthrough-mcp/aenderungen