Official vendor OpenAPI document · agent-readySocial MediaSocial Listeningbearer36 EndpointsREST
For Agents
Search YouTube transcripts for timestamped mentions of entities and topics, resolve names to canonical entities, and set up monitors that fire webhook alerts on new mentions.
Use for: I need to find YouTube mentions of a specific brand, I want to resolve a person's name to a canonical entity id, Search transcripts for passages that discuss a product, Find all channels that recommend a competitor
Not supported: Does not handle video hosting, payments, or written social posts. Use for searching and monitoring spoken mentions in YouTube transcripts only.
The Arcmira API searches YouTube transcripts for timestamped passages where people, organizations, products, and topics are spoken about. It resolves a name to a canonical entity, returns ranked mentions and recommendations across indexed channels, pulls full creator captions or Premium whole-video quotes, and surfaces channel sponsor and coverage data. Monitors and trackers watch chosen entities and fire webhook alerts when new mentions appear, so an agent can follow the spoken web rather than poll it.
Install Jentic One Beta
Connect the Arcmira API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Arcmira API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Farcmira.com%2Farcmira" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Farcmira.com%2Farcmira" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with Arcmira API.
Resolve a spoken name to one canonical entity id before filtering results
Search transcript passages across indexed channels for a person, product, or topic
Rank mentions and recommendations to find who is talking about an entity
Pull a video transcript or a Premium whole-video quote with speaker identification
List a channel's recurring sponsors and index coverage
Create monitors and trackers that fire webhook alerts when new mentions appear
Use Cases
Patterns agents use Arcmira API for, with concrete tasks.
★ AI agent mention monitoring via Jentic
An AI agent connected through Jentic watches the spoken web for a brand without browsing Arcmira's reference docs. The agent searches by intent such as finding mentions of an entity, Jentic returns the matching Arcmira operation with its input schema, and the agent resolves the name to a canonical entity, searches ranked mentions, and creates a monitor that fires a webhook when new passages appear. Credentials are injected by the developer's own Jentic One instance at call time.
Resolve a brand name with GET /v1/entities/resolve, call GET /v1/mentions for that entity id, then POST /v1/monitors to alert on new mentions
Competitive and sponsor research
Research teams map who is talking about a product and which creators drive recommendations. Arcmira ranks mentions and recommendations across indexed channels, lists a channel's recurring sponsors, and reports what the index holds for a channel, so an agent can assemble a share-of-voice picture from spoken content rather than written posts.
Call GET /v1/recommendations for a product entity, then GET /v1/channels/{channel_id}/sponsors to list a creator's recurring sponsors
Transcript retrieval for citation
Content and research tools need the exact spoken passage, not a paraphrase. Arcmira returns timestamped transcript slices for a topic and can quote a Premium whole-video transcript with speaker identification, letting an agent cite the moment a claim was made and link back to the source video.
Call GET /v1/search for a topic to get timestamped slices, then GET /v1/transcripts/{video_id} to pull the full transcript
Standing entity surveillance
Analysts track named entities over time instead of running ad hoc searches. Arcmira monitors and trackers follow chosen entities, record momentum for an entity, and deliver recent alerts, so an agent is notified of new spoken mentions through a signed webhook as they are indexed.
POST /v1/monitors to create a monitor, POST /v1/monitors/{id}/entities to follow entities, then GET /v1/monitors/{id}/alerts to read recent alerts
Key Endpoints
36 endpoints — the arcmira api searches youtube transcripts for timestamped passages where people, organizations, products, and topics are spoken about.
METHOD
PATH
DESCRIPTION
GET
/v1/entities/resolve
Resolve a name to one entity id
GET
/v1/mentions
Search mentions across media
GET
/v1/recommendations
Search recommendations across media
GET
/v1/search
Retrieve transcript slices for a topic
GET
/v1/transcripts/{video_id}
Get a video transcript
GET
/v1/channels/{channel_id}/sponsors
List recurring channel sponsors
POST
/v1/monitors
Create a monitor
GET
/v1/monitors/{id}/alerts
List recent monitor alerts
GET
/v1/entities/resolve
Resolve a name to one entity id
GET
/v1/mentions
Search mentions across media
GET
/v1/recommendations
Search recommendations across media
GET
/v1/search
Retrieve transcript slices for a topic
GET
/v1/transcripts/{video_id}
Get a video transcript
GET
/v1/channels/{channel_id}/sponsors
List recurring channel sponsors
POST
/v1/monitors
Create a monitor
GET
/v1/monitors/{id}/alerts
List recent monitor alerts
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
A
Arcmira API
- AI-Aware (A-)70/100
93
Foundational Compliance66
Developer Experience & Jentic Compatibility57
AI-Readiness & Agent Experience94
Agent Usability60
Security69
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
93
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A+Signals: 4
96%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
75%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
66
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: BSignals: 4
1%
Example Density
How richly the API is illustrated with examples.
89%
Example Validity
Percentage of examples that conform to their schemas.
75%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
57
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: CSignals: 4
78%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
97%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
53%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
60
Security
Trust, risk posture, and security compliance.
Grade: B-Signals: 1
60%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
69
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: B+Signals: 1
69%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Arcmira API by hand means learning its bearer scheme, resolving names to entity ids before every filter, and standing up a webhook receiver for monitor alerts. Through Jentic you install once, import Arcmira from the API Directory, store the token once, and your agent calls the search and monitor operations.
Permission scoping
Arcmira puts the resource id in the URL path for monitors and trackers (/v1/monitors/{id}, /v1/trackers/{id}), so a rule can pin your agent to the read side: resolve entities, search mentions, and fetch transcripts. You choose the operations it may call, so state-changing ones like monitor deletion or webhook-secret rotation are not included unless you add them.
Credential isolation
Your Arcmira bearer token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'find mentions of a brand' or 'get a video transcript', and Jentic returns the matching Arcmira operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Arcmira API through Jentic.
What authentication does the Arcmira API use?
The Arcmira API authenticates with an HTTP bearer token in the Authorization header, per its OpenAPI spec. A few operations need no credential, such as the health check and signup verification, while the search, transcript, and monitor endpoints use the bearer token. Through Jentic, your token is stored encrypted by your own Jentic One instance and injected at execution time, so it never enters the agent's prompt or logs.
Can I search YouTube transcripts for a specific brand with the Arcmira API?
Yes. Resolve the brand to a canonical entity id with the entity resolve operation, then call the mentions search to get ranked, timestamped passages where it is spoken about across indexed channels. You can also pull the full transcript for any returned video to cite the exact moment.
What are the rate limits for the Arcmira API?
The OpenAPI spec does not specify rate limits, and Premium transcript reads draw credits from the account plan. Check the Arcmira documentation at https://arcmira.com/docs for current limits and credit costs before running high-volume searches.
How do I monitor new mentions through Jentic?
Search Jentic by intent such as monitoring an entity, and it returns the Arcmira monitor-create operation with its input schema. Create a monitor, follow entities on it, and read recent alerts through the monitor alerts operation, with your credential injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Arcmira API?
Yes. Write a rule that allows only the entity resolve, mentions search, and transcript read operations, so the agent can research spoken mentions but cannot create or delete monitors or rotate a webhook signing secret, and every call it makes is logged by your self-hosted instance.
Is there an Arcmira API MCP server?
You do not need an MCP server to give your agent the Arcmira API. Jentic connects it directly from the API Directory: import Arcmira, store your bearer token once, and your agent calls the search and monitor operations on demand without loading another server's tool definitions into its context.
GET STARTED