Video → LLM Analyzer
Pricing
from $0.008 / analysis completed
Drop a video, give it a prompt, and have an LLM analyze it. Results land in your Notion page so Claude Code can pick up where you left off. Uses Apify MCP Connectors to write to Notion on your behalf — no Notion API key required.
New input allowLongVideos (default false) lifts the 10-minute duration cap
for users who accept the higher, harder-to-estimate cost. Off, nothing changes.
maxChargeUsd — which still works: the
post-ingest worst-case estimate uses the real duration, so a cap aborts
before the LLM call exactly as before.softErrors.whisper message instead of burning a doomed API upload. The
constant is decimal 25,000,000 bytes so the "~69 minutes" copy is exact and
the guard is conservative (review catch: 25 MiB would shift the boundary to
~73 min and could let a doomed upload through).resolve_charge_cap() / publisher_fees_estimate_usd()
helpers, and the refined gate's abort message now names any Whisper spend
that already happened.allowLongVideos joins the idempotency key (review blocker fix): the
fallback copy tells users to flip the flag and re-run; without the flag in
the key that exact re-run replayed the stale transcript-only result.
Existing idempotency entries miss once and recompute; the analysis cache
still absorbs the LLM cost where the resolved mode matches.whisper_used (which added a phantom per-minute
term to cost estimates) or clobbers a preserved caption transcript; it now
soft-errors "no audio track".softErrors — output-schema addition,
separate change.Fixes the three bugs found in the 2026-08-03 demo-review runs (fCaYYYdXwRagdgqiE,
TuRJhQp0HXRnbsugw). No input schema changes; one new analysisMode value.
streamers/youtube-scraper returns
captions as one complete raw SRT per subtitles entry ({language, srt}), not
the {text, start} segment shape the extractor expected — so runs recorded
transcriptChars: 0 while a 50 KB SRT sat in the response. Added an SRT
flattener (strips indices, timestamps, and the rolling-caption duplicates
auto-generated tracks emit). The demo video now yields 12,050 transcript chars.softErrors.youtubeTranscript used to stay
null unless BOTH transcript and title were missing. It now reports the
metadata-present-but-no-captions case, with the recovery step in the message.transcript+thumbnail and the LLM was told to lean on a transcript
that wasn't there — which produced confident fabricated reviews. Those runs are
now labeled analysisMode: "thumbnail" (new value, documented in the README),
and the prompt tells the model it has one still image, forbids inventing
content, and redirects it to what the thumbnail and metadata do show.thumbnail runs refuse mode-less
pre-2.7 cache entries.download_via_actor retries once after a 10 s pause on
infra failures (launch timeouts), with a log line for the wait. Deterministic
failures are not retried. This does not fix a persistently-down downloader —
a second fallback is a known follow-up, not in this build.analysisMode contract test that fails if the code and
README enum drift).Build reproducibility and memory rightsizing. No input/output schema changes.
requirements.lock, a fully pinned,
hash-verified resolution compiled from requirements.txt. The Docker build now
installs from it with pip install --require-hashes -r requirements.lock instead
of from the loose ranges. This pins apify-shared (currently 2.2.0) — the
transitive dependency behind the v2.x crash — so a rebuild can't silently pull a
changed version. requirements.txt keeps the human-readable ranges and is the
source the lock is compiled from. Regenerate the lock after editing
requirements.txt with:
uv pip compile requirements.txt -o requirements.lock --generate-hashes --no-header --python-version 3.14
(--python-version 3.14 matches the apify/actor-python:3.14 base image;
pre-releases are excluded by default). The lock in this commit was generated this
way on a connected machine, not hand-written..actor/actor.json from min 2048 / max 4096 MB to
min 1024 / max 2048 MB. Peak observed Python RSS was ~114 MB; the 2 GB max keeps
headroom for the ffmpeg subprocess (whose RSS is not in that 114 MB number) while
halving the per-GB actor-start charge.
Error-handling hardening. No input/output schema changes; existing Tasks keep working.
main(). An unhandled error now fails the
run with a failed_internal dataset row (errorCategory: internal_error,
errorRecoverable: false) and a human status message, instead of exiting with
a bare exit_code 1 and no explanation.RuntimeErrors from the LLM paths
(transport, 4xx/5xx, out-of-credit, rate limit) stay user-friendly and
recoverable. Any other exception is treated as an internal error (permanent),
so a bug isn't mislabeled as a retryable LLM condition and looped on by agents.First release built from the GitHub repo (private) rather than uploaded source files.
For 2.7 and earlier, see the Apify Console build history and the project notes.