Langbly Translation API
69
AI ReadinessAI-Aware (B+)69/100
Official vendor OpenAPI document · agent-readyAI/MLLanguage Modelsbearer3 EndpointsREST
For Agents
Translate one or many strings into a target language with optional formality and HTML preservation, detect the language of text, and list supported languages, using Google Translate v2 request shapes.
Use for: Translate this product description into Dutch, Translate these five UI strings from English to German, Detect which language this customer message is in, List all languages Langbly supports
Not supported: Does not handle document file translation, speech translation, or localisation project management. Use for translating text strings, detecting their language, and listing supported languages only.
The Langbly Translation API translates text with context, reading full sentences rather than word by word, and uses the same request and response format as the Google Translate v2 API, so existing clients switch by changing the endpoint. It translates a single string or an array of strings into a target language, preserves HTML markup when format is html, and takes a formal, informal, or neutral formality where the language supports it. Companion operations detect the language of text with a confidence score and list the supported languages.
Install Jentic One Beta
Connect the Langbly Translation API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Langbly Translation 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%2Flangbly.com%2Flangbly" | 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%2Flangbly.com%2Flangbly" | 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 Langbly Translation API.
Translate a single string or an array of strings into a target language, with source auto-detected when omitted
Preserve HTML markup while translating by setting format to html
Request a formal, informal, or neutral formality where the target language supports it
Detect the language of one or more strings with language, isReliable, and confidence for each
List the supported languages, with names localised into a chosen target language
Swap in for the Google Translate v2 API using the same request and response format
Use Cases
Patterns agents use Langbly Translation API for, with concrete tasks.
★ Batch UI String Translation
A localisation agent sends an array of interface strings in one translate call with source and target set, and receives translatedText for each in the same order. Because the response matches the Google Translate v2 shape, existing parsers keep working, and format html keeps any inline markup intact.
Call POST /language/translate/v2 with q ['Save changes', 'Cancel', 'Your order has shipped'], source 'en', and target 'de', then map each translatedText back to its string key
Customer Message Language Detection
Before routing a support message, the agent detects its language and checks isReliable and confidence, then translates it into the team's working language. Leaving source empty on the translate call also returns detectedSourceLanguage, so a single call can do both when confidence is not needed.
Call POST /language/translate/v2/detect with q 'Bonjour, ma commande est en retard', then POST /language/translate/v2 with the same q and target 'en'
Migrating from Google Translate v2
Teams already calling the Google Translate v2 API can point the same requests at Langbly: the translate, detect, and languages operations share the request and response format. An agent can verify parity by sending identical q, target, and format values and comparing the translations field.
Call GET /language/translate/v2/languages with target 'en' to confirm the needed languages are supported, then send an existing Google Translate v2 request body to POST /language/translate/v2
AI Agent Translation via Jentic
An AI agent translates content through Jentic without holding the Langbly key. It searches by intent, receives the translate operation with its input schema, and executes with the bearer key injected at run time, so translating a reply or a document is one step in a larger multilingual workflow.
Search Jentic for 'translate text into another language', load the translateText schema, and execute it with q, target 'fr', and formality 'formal'
Key Endpoints
3 endpoints — the langbly translation api translates text with context, reading full sentences rather than word by word, and uses the same request and response format as the google translate v2 api, so existing clients switch by changing the endpoint.
METHOD
PATH
DESCRIPTION
POST
/language/translate/v2
Translate text
POST
/language/translate/v2/detect
Detect language
GET
/language/translate/v2/languages
List supported languages
POST
/language/translate/v2
Translate text
POST
/language/translate/v2/detect
Detect language
GET
/language/translate/v2/languages
List supported languages
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.
L
Langbly Translation API
- AI-Aware (B+)69/100
100
Foundational Compliance73
Developer Experience & Jentic Compatibility50
AI-Readiness & Agent Experience94
Agent Usability60
Security71
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
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.
73
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: A-Signals: 4
41%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
50%
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.
50
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: D+Signals: 4
36%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
62%
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).
71
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A-Signals: 1
71%
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 Langbly by hand means attaching the bearer key, shaping Google Translate v2 style bodies, and backing off when the translate call is rate limited. Through Jentic you install once, import Langbly from the API Directory, store the key once, and your agent calls it.
Permission scoping
Langbly carries the text and target language inside the request body, so rules bound which operations your agent may call, not which languages or text it sends. Limit the agent to the operations it needs, such as detection only or translation only.
Credential isolation
Your Langbly API 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 'translate text into another language' or 'detect the language of a message', and Jentic returns the matching Langbly 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 Langbly Translation API through Jentic.
What authentication does the Langbly Translation API use?
Per its OpenAPI spec, the Langbly Translation API uses the bearerAuth scheme: your API key passed as a bearer token, Authorization: Bearer YOUR_API_KEY. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never enters the agent's context.
Is the Langbly Translation API compatible with Google Translate v2?
Yes. The spec describes it as a drop-in replacement for the Google Translate v2 API with the same request and response format: q, target, source, and format on the request, and data.translations with translatedText and detectedSourceLanguage on the response. Langbly adds an optional formality field of formal, informal, or neutral.
What are the rate limits for the Langbly Translation API?
The OpenAPI spec defines a rate-limited response on the translate operation but does not state a numeric limit. Check https://langbly.com for the limits on your plan, and back off when that response is returned.
How do I translate text through Jentic with the Langbly Translation API?
Search Jentic for 'translate text into another language' and it returns the translateText operation with its input schema. Execute POST /language/translate/v2 with q (a string or array) and target, plus optional source, format, and formality. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a Langbly MCP server?
You don't need an MCP server to give your agent the Langbly Translation API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it. Operations are discovered by intent on demand, so no extra tool definitions are loaded into the agent's context.
Can I limit what my agent is allowed to do with the Langbly Translation API?
Yes. A triage agent can be allowed only the detect and languages operations, so it can identify a message's language without spending translation volume. Add the translate operation when the agent should produce translations, and every call it makes is logged by your own instance.
GET STARTED