Skip to main content

Arcmira for Python

YouTube transcript search and monitoring for your AI: exact quotes, full transcripts and speakers.

Arcmira · Get an API key · API docs · Pricing

Install

uv add arcmira

pip install arcmira works too. Set ARCMIRA_API_KEY to your API key. Save an example as example.py and run python example.py in your environment.

Search YouTube videos and podcast transcripts for quotes and clips

Find what people are saying about a company, product, or idea across YouTube videos and podcasts. Search phrases such as GPU demand, GPU financing, or inference costs; narrow by speaker, company, channel, or date as your question develops. Start with GPU demand over the last 60 days.

from datetime import datetime, timedelta, timezone
from urllib.parse import urljoin
from arcmira import Arcmira

client = Arcmira()
query = "GPU demand"

# Search the last 60 days.
now = datetime.now(timezone.utc)
after = (now - timedelta(days=60)).isoformat()
before = now.isoformat()

hits = client.transcripts.search(q=query, after=after, before=before, limit=20)
print(f"\n{query} ({len(hits.chunks)} passages)")
print(
    f"{(hits.window.after or 'unknown')[:10]} - "
    f"{(hits.window.before or 'unknown')[:10]}\n"
)
for i, hit in enumerate(hits.chunks, 1):
    print(f"{i:02d}\n{hit.text}\n")
    print(f"Video:      {hit.video_title or hit.video_id}")
    print(f"Channel:    {hit.channel_name or 'Unknown'}")
    print(f"Published:  {(hit.published_at or 'Unknown')[:10]}")
    print(f"Transcript: {hit.source_label or 'Unknown'}")
    print(f"Watch:      {urljoin('https://arcmira.com', hit.watch_url)}\n--\n")

Sample console output

The script prints every returned passage in full. Below is an excerpt from result 13 of the October 16, 2026 run, wrapped for readability. ... marks omitted output. Your results will vary.

GPU demand (20 passages)
2026-08-17 - 2026-10-16

...

13
...
John Coogan: What is the next couple months even look like for CPU demand in the
data center?
Cristiano Amon: Okay, let me separate that conversation into— I think one, one
topic is there's so much more demand for compute than availability right now and
across the board.
Cristiano Amon: So I think what we're seeing this right now and by the way, as a
semiconductor company, I'll tell you, this supply chain, it's operating at 100%
capacity, everything Everything is short because there's so much more demand

Video:      Jensen vs NYT, New Model Reactions, Saudi EVs, You Can See
            Everything
Channel:    TBPN
Published:  2026-09-23
Transcript: Arcmira Premium
Watch:      https://arcmira.com/watch?v=wDWgNOpna90&t=2428
--

...

Use hits.chunks directly for further analysis; the logging above is for inspection.

Find evidence that could change your mind. Strong demand is the beginning of the investigation. Follow the other results into customer commitments, margins, and financing, compare conflicting claims, and build a research brief with timestamped sources.

Learn how to investigate a research question with YouTube video and podcast transcript search in our Guide.

Give your agent access to the latest indexed conversations, speaker-labeled Premium transcripts, and company alerts. The most up-to-date coverage is only available via paid plans, starting at $20/month. Try Pro free for 7 days at no risk. Put Arcmira to work on a real research question, then keep it only if it earns a place in your research stack.

Not ready for a paid plan? Tell us why and what you would pay for. Feedback is free to give and helps us build what you want.

Search covers indexed transcripts within your plan's date window. Missing a source you care about? Help shape the index with the channels or industries you need and what better coverage would make possible.

Transcribe a YouTube video

Start free with 1,000 credits a month, enough for up to 250 caption transcripts of videos up to 15 minutes each. Captions use 4 credits per started 15 minutes from the same balance as search and alerts. Plans and usage.

Pull an available YouTube caption track with timestamps. Replace the video id below with yours.

Keep the names your research depends on. Misheard company and product names can send an agent to the wrong entity. In a spelling-based review across 167 tech and finance videos, name disagreements favored Premium over YouTube automatic captions by about 21:1. Use Premium for speaker labels and research where names matter.

This measures the tested name disagreements, not overall word accuracy. How we measured this.

from arcmira import Arcmira

client = Arcmira()
transcript = client.transcripts.get("dQw4w9WgXcQ")
if transcript.state == "ready":
    for line in transcript.lines or []:
        print(line.start, line.text)

Get a free cost estimate with client.transcripts.quote(video_id), then read with quality="premium". Premium uses credits from your plan, then your on-demand budget. If pending, poll after job.next_poll_seconds. Premium states, polling, and retries.

Set up YouTube monitoring for your company

Follow 2 names and get up to 40 alerts a month on a free account, if you use all 1,000 monthly credits for alerts. Each alert uses 25 credits once per occurrence, regardless of delivery channels or recipients. Get alerts as new mentions are analyzed, by email or Slack, or use a webhook on a paid plan.

Follow your company or a competitor in newly analyzed YouTube videos and podcasts. Replace PlanetScale and you@example.com below. External email recipients must confirm before delivery.

from arcmira import Arcmira
from arcmira.monitors import AddEntitiesRequestNamesItem

client = Arcmira()
created = client.monitors.create(
    name="Company watch",
    notify_frequency="realtime",
    notify_emails=["you@example.com"],
)
added = client.monitors.entities.add(
    created.monitor.id,
    names=[AddEntitiesRequestNamesItem(name="PlanetScale", type="organization")],
)
for result in added.results:
    print(result.tracker_id if result.attached else result.reason)

This creates a monitor and tracker in your account. Check each attached result. Alerts cover newly analyzed episodes published within the last 14 days. For retries of writes, reuse the same idempotency_key.

Choose the next task

Task SDK call
Find a company, person, or show entities.resolve(q=..., context=...)
Read mentions of an entity mentions.list(entity_id=...)
Find a channel's sponsors channels.sponsors.list(channel_id)
Separate recommendations from paid mentions recommendations.list(entity_id=..., class_="organic")
Read alerts from a monitor monitors.alerts.list(monitor_id)

Entity filters take ids. Resolve names first; explain a suggested match and ask the user when the resolver returns ask. Use after inclusive and before exclusive for date windows. Paginated methods fetch more rows as you iterate, so stop when you have enough.

AsyncArcmira provides the same methods asynchronously. Await the first page, then use async for for paginated results.

Use Arcmira with an AI agent

Add "use arcmira" to any question to send it to Arcmira first.

For tasks such as "pull YouTube transcripts", "find quotes with timestamps", "research podcast sponsors", or "monitor company mentions", connect the Arcmira MCP server. The agent index links to current API and citation guidance.

Reference

Requires Python 3.9+. Apache-2.0. Source · License.

Metadata

Release files for arcmira 0.6.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for arcmira 0.6.3
File Size Uploaded Provenance Actions
arcmira-0.6.3.tar.gz 144.7 kB Without provenance Details for arcmira-0.6.3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for arcmira 0.6.3
File Interpreter ABI Platform Actions
arcmira-0.6.3-py3-none-any.whl Python 3 none any Details for arcmira-0.6.3-py3-none-any.whl

Total release size: 483.6 kB

Release files / arcmira-0.6.3.tar.gz

Download URL arcmira-0.6.3.tar.gz
Size 144.7 kB
Tags Source
SHA-256 checksum
How to use checksums
a1565fe22af801f0dc835f0340d7a1fb7c93ab2f1d776fee69b1892c9ebf5179
BLAKE2b-256 checksum
How to use checksums
cf958f73755b17fcb82320593805671a03786630e6473dc7d3bbeb352a47e22d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / arcmira-0.6.3-py3-none-any.whl

Download URL arcmira-0.6.3-py3-none-any.whl
Size 338.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
35ee38f165a28b48a53bcff8aa475be9a7f90ff7e445a7ae4667602a6421e101
BLAKE2b-256 checksum
How to use checksums
a6799d1863ff20a5a7866965cc83c87220d3ae6a2483ca639cdc0ae0c71037fb
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Security for arcmira 0.6.3

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page