Install Jentic One Beta

Connect the ManyScripts API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the ManyScripts 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.

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%2Fmanyscripts.com%2Fmanyscripts" | sh

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%2Fmanyscripts.com%2Fmanyscripts" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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 ManyScripts API.

Extract the spoken transcript from a single social video URL in one call

Return the creator's written caption separately from the spoken words, truncated to 2200 characters

Read engagement metadata such as viewCount, likeCount, commentCount, and shareCount with each transcript

Get video context fields including title, uploader, duration, uploadDate, and hashtags

GET STARTED

Start building with ManyScripts API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use ManyScripts API for, with concrete tasks.

★ Video research agent through Jentic

A research agent receives a list of video links and needs their content as text. Through Jentic it calls the ManyScripts transcript operation for each URL, reads the transcript and caption, and passes them on for summarising or tagging. The msk_ key is injected by Jentic at call time, so the agent never sees it.

POST /transcript with url 'https://www.tiktok.com/@user/video/123456789', read transcript and caption from the response, and return a three-line summary of what the creator says

Content repurposing from short-form video

Creators and marketers turn short videos into blog posts, threads, or captions for other platforms. The transcript gives the spoken script, the caption field carries what the creator wrote, and hashtags show how the post was tagged, so a writing tool has all three inputs from one call.

POST /transcript for an Instagram Reel URL, combine transcript, caption, and hashtags, and draft a short article outline from them

Engagement snapshot for a video

Alongside the words, each extraction returns viewCount, likeCount, commentCount, and shareCount plus uploadDate. Social analysts can log these figures per video to compare how different scripts performed. The spec notes shareCount is well populated on TikTok and often absent elsewhere, so treat it as optional.

POST /transcript for three video URLs, record viewCount, likeCount, and commentCount for each, and rank them by views

Connection test before a batch run

Integration platforms need to confirm a saved key works before queuing extractions. The account check returns userId, plan, and apiAccess, and apiAccess is false on a free plan where the transcript endpoint answers 403. It runs no extraction and costs nothing.

Call GET /me, confirm apiAccess is true and plan is 'pro', and stop with a clear message if it is not

Key Endpoints

2 endpoints — the manyscripts api extracts the spoken transcript, the creator's written caption, and public metadata from a social video link.

METHOD

PATH

DESCRIPTION

POST

/transcript

Extract a video transcript, caption, and metadata

GET

/me

Check an API key and its plan

POST

/transcript

Extract a video transcript, caption, and metadata

GET

/me

Check an API key and its plan

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring ManyScripts by hand means handling its msk_ bearer key and reading three different 429 shapes to know when to back off. Through Jentic you install once, import the ManyScripts API from the API Directory, store the key once, and your agent calls it.

Permission scoping

ManyScripts takes the video link in the request body, so rules bound which operations your agent may call, not which videos. Limit the agent to the operations it needs, such as transcript extraction or the free key check.

Credential isolation

Your ManyScripts key 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 'get the transcript of a TikTok video', and Jentic returns the matching ManyScripts operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using ManyScripts API through Jentic.

Is there a ManyScripts MCP server?

You don't need an MCP server to give your agent the ManyScripts API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it. The transcript operation is found by intent when needed, so no extra tool definitions sit in the agent's context.

What authentication does the ManyScripts API use?

Per its OpenAPI spec, the ManyScripts API uses a bearer token: your ManyScripts API key, which starts with msk_, sent in the Authorization header. Keys are generated in the ManyScripts dashboard under Connect & Integrations. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time.

Which platforms does the ManyScripts API support?

The transcript operation lists YouTube, TikTok, Instagram Reels, X/Twitter, and Facebook, and the API description also mentions Xiaohongshu in beta. An unsupported platform, a private video, or a video with no speech returns 400 with a code such as NO_SPEECH or PRIVATE_VIDEO and a retryable flag.

What are the rate limits for the ManyScripts API?

The spec documents 60 requests per minute and a daily extraction limit of 1,000 a day by default, reset at 00:00 UTC. A link that failed in the last 30 minutes with a non-retryable answer triggers a cooldown. All three return 429 with a Retry-After header, and the body says which limit applied.

Can I limit what my agent is allowed to do with the ManyScripts API?

Yes. Write a rule that allows only POST /transcript, so the agent can pull transcripts for the links you give it and nothing more, or allow only GET /me for a connection check that never spends an extraction. Every call it makes runs through your own instance.

How do I get a video transcript with the ManyScripts API through Jentic?

Add the ManyScripts API to Jentic One from the directory and store your msk_ key once. Your agent searches for 'get the transcript of a video', calls POST /transcript with the video url, and reads transcript, caption, and metadata from the response. To run it on your own infrastructure, install Jentic One from its GitHub repo.

ManyScripts API

AI ReadinessAI-Aware (A-)70/100

See full scorecard

Official vendor OpenAPI document · agent-readyAI/MLSpeechbearer2 EndpointsREST

For Agents

Turn a TikTok, YouTube, Instagram, X/Twitter, or Facebook video URL into its spoken transcript, caption, and engagement metadata, and check whether a key has API access.

Use for: I want the transcript of this TikTok video, Get the spoken words and caption from a YouTube link, Extract what the creator says in an Instagram Reel, Find the hashtags and view count for this video

Not supported: Does not transcribe uploaded audio files, download video media, or post to social platforms. Use for extracting transcripts and metadata from public social video links only.

The ManyScripts API extracts the spoken transcript, the creator's written caption, and public metadata from a social video link. You send one video URL from YouTube, TikTok, Instagram Reels, X/Twitter, or Facebook, and it returns the transcript alongside the title, uploader, duration, upload date, hashtags, and view, like, comment, and share counts. A second call checks which account a key belongs to and whether its plan can call the transcript endpoint, without running an extraction.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

100

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

99%

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).

100%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: BSignals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

62%

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.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: C-Signals: 4

57%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

50%

Summary Coverage

Coverage of summaries across operations/tags/info.

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.

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).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: ASignals: 1

88%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the ManyScripts API to your agent

Capabilities

Start building with ManyScripts API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

ManyScripts API

Jentic AI Readiness Score

ManyScripts API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness