Status today's ingestion spend

Read directly from where each cap mechanism already tracks itself, not re-derived here.

What this is. A record of when a stock was said out loud in tracked market-commentary videos, and where in the video. It is a citation index, not analysis.

Not a recommendation. A mention here is not a buy, sell, or hold signal, and is not endorsed, scored, or ranked by this tool in any way -- see every result for what a channel said, not what this product thinks about it.
Automated speech-to-text and automated matching. Transcripts are machine-generated and mention detection is automated; both can misfire. Always confirm by watching the linked moment before relying on what a card says was said.
Coverage is partial. Only the tracked channels and videos this product has actually processed are searchable. No result for a symbol in a window does not mean it was not discussed anywhere -- only that it was not found in what has been indexed so far.

YouTube Data API quota units

0/10000

0% of today's budget

TranscriptAPI fetch attempts

0/20

0% of today's cap

OpenRouter calls (AI Research digest)

5/0

Model anthropic/claude-sonnet-5-20260630 · not configured on this deployment (no key set), so nothing can be sent. Attempts, failed ones included, per UTC day — the same unit as the transcript cap above.

Ingestion backlog (discovered, transcript not yet fetched)

not available

No daily ceiling of its own — nothing to gauge against, so nothing is drawn.

NSE regular session 09:15-15:30 IST — the exchange's published hours, shown as context for when commentary is recorded. This index carries no live market data and no prices; nothing on this page moves with the market.

Only backfill_youtube_channel_uploads.py runs are counted here so far -- discover_youtube_candidates.py is not yet wired into the ledger (see this module's docstring).

Backlog is exactly what the transcript collector would plan next with no cap applied (its own selection logic, same success/failed stores). It is worked through newest-first, 20 attempts per UTC day, and already-attempted videos are never re-spent on -- so a backlog larger than the daily cap is expected while the channel roster is being caught up.