About io.github.korovin-aa97/talkthrough-mcp
io.github.korovin-aa97/talkthrough-mcp is an MCP server published by korovin-aa97 in the AI category: narrated screen recordings into agent-ready data: local transcript, keyframes, OCR, wall-clock.
The repository has 32 stars and 4 forks, with the last commit yesterday. Recent commit activity is the strongest signal that reported issues will get attention.
Install
uvx talkthrough-mcppip install talkthrough-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (9)
extract_frame(job_id, at_ms, crop?)Exact-timestamp full-resolution re-extract from the source video (optional crop) when keyframes miss the instant; returns the file's absolute `path`. URL jobs decode their kept source — no network.
Parameters not published.
get_frames(job_id, at_ms? \start_ms?+end_ms?, max_frames?, include_duplicates?)`
Parameters not published.
get_moment(job_id, start_ms, end_ms)The "one remark" bundle: transcript slice + up to 3 frames + their OCR text + wall-clock range (+ `speakers_in_range` when diarized).
Parameters not published.
get_transcript(job_id, start_ms?, end_ms?, format?)Paginated transcript as `segments`, `text`, or `srt` (speaker-prefixed when diarized, plus a roster header); truncation returns `next_start_ms`.
Parameters not published.
label_speakers(job_id, labels, evidence?)Atomically persist verified names for anonymous speaker labels. Raw `S1`/`S2` labels remain canonical; blank/null removes a name.
Parameters not published.
list_jobs()Recent processed recordings with source paths, durations, wall-clock starts, counts, speaker counts when diarized, and the provider/id for URL jobs.
Parameters not published.
process_media(path, recorded_at?, vocabulary?, language?, model?, diarize?, num_speakers?, force?)Ingest a video/audio file: local STT, keyframes, OCR, wall-clock, opt-in speaker labels. Returns a compact summary. Idempotent by content hash — re-calls are instant; `diarize=true` on a processed job adds speakers without re-transcribing.
Parameters not published.
process_url(url, recorded_at?, vocabulary?, language?, model?, diarize?, num_speakers?, refresh?, force?)The one network tool: download one public video/audio URL once (a direct `https://` media link, one YouTube video, or any public video page yt-dlp can read — with the `[url]` extra), keep the source inside the job, then run the same local pipeline. Same-URL re-calls serve the stored job without network unless `refresh=true`; `force=true` rebuilds from the kept source; the raw URL is never stored.
Parameters not published.
search(job_id, query, speaker?, match_mode?)Substring search over the transcript AND on-screen OCR text. `all_words` remains the default; `any_word` broadens lexical recall. Hits carry `t_ms`/`t_wall`, frame refs, and the speaker when diarized. The optional filter accepts a raw label or saved name.
Parameters not published.
Ask AI
Ask AI about io.github.korovin-aa97/talkthrough-mcp
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.