Install Jentic One Beta

Connect the DialValet API (current beta implementation) to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the DialValet API (current beta implementation), 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%2Fdialvalet.com%2Fdialvalet" | 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%2Fdialvalet.com%2Fdialvalet" | 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 DialValet API (current beta implementation) API.

Request one outbound AI-voiced phone call with a chosen GPT-Live voice

Watch a call's live streaming transcript and poll its state and result

Steer the live agent mid-call and answer the questions it raises

Retrieve or delete a call transcript and its encrypted structured result

GET STARTED

Start building with DialValet API (current beta implementation) API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use DialValet API (current beta implementation) API for, with concrete tasks.

★ An Agent Placing a Call on Your Behalf

An AI agent connected to DialValet through Jentic can place an outbound call to a number, choose a GPT-Live voice, and let the platform speak on the user's behalf, for errands like confirming an appointment or asking a business a question. Placing a call requires a verified caller ID, available prepaid credit, and passing account limits, so the agent works within guardrails the account owner set.

Request an outbound call to a business number with a selected voice and poll the call until it reaches a completed state

Live Supervision and Steering

While a call is running, DialValet streams a live transcript and lets a supervisor or agent steer the live agent to correct or add information, and answer any pending questions the live agent raises before it continues. This keeps a human or orchestrator in the loop on a voice call rather than committing to a fully scripted flow.

Watch a call's live transcript, answer a pending live-agent question, and send a steer message to correct a detail

Caller-ID Verification and Prepaid Billing

Before any call, DialValet verifies caller identities with a code and lets you select a verified default, and it runs on a prepaid wallet with a balance, a ledger of credits and charges, and a one-time Stripe Checkout to top up. This keeps outbound calling tied to a verified number and to credit the account actually holds.

Send a caller-ID verification code, confirm it, set it as the default, and read the prepaid wallet balance

Transcript Retrieval and Data Deletion

After a call, DialValet produces a transcript and an encrypted structured result that can be requested, and both can be deleted on demand through dedicated routes. This supports a retention policy where an agent reads what it needs from a call and then removes the stored content.

Request the transcript for a completed call, extract the outcome, then delete the encrypted structured result

Key Endpoints

37 endpoints — the dialvalet api places outbound phone calls voiced by a gpt-live agent: an agent requests one call to a number, picks a voice, and the platform dials and speaks.

METHOD

PATH

DESCRIPTION

POST

/calls

Request one outbound call

GET

/calls/{call_id}

Get call state and result

GET

/calls/{call_id}/live

Watch the live call transcript

POST

/calls/{call_id}/steer

Correct or inform the live agent

POST

/calls/{call_id}/guidance/{request_id}/answer

Answer a pending live-agent question

GET

/calls/{call_id}/transcript

Request a call transcript

POST

/caller-identities/verification

Send a caller-ID verification code

GET

/voices

List GPT-Live agent voices

POST

/calls

Request one outbound call

GET

/calls/{call_id}

Get call state and result

GET

/calls/{call_id}/live

Watch the live call transcript

POST

/calls/{call_id}/steer

Correct or inform the live agent

POST

/calls/{call_id}/guidance/{request_id}/answer

Answer a pending live-agent question

GET

/calls/{call_id}/transcript

Request a call transcript

POST

/caller-identities/verification

Send a caller-ID verification code

GET

/voices

List GPT-Live agent voices

Why Jentic?

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

Setup

Wiring DialValet by hand means handling its bearer auth (a dv_live_ key or a dv_session cookie), verifying a caller ID, keeping prepaid credit topped up, and staying inside account limits, all in a U.S.-only beta. Through Jentic you install once, import DialValet from the API Directory, store the key once, and your agent calls it.

Permission scoping

DialValet puts each call's id in the URL path (/calls/{call_id}/...), so a rule can let your agent place calls and watch and steer a specific call while account deletion, API-key revocation, and billing checkout stay out of its reach. You choose the operations it may call, so nothing that closes your account or spends on credit runs unless you add it.

Credential isolation

Your DialValet 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 'place an outbound call' or 'watch a live call transcript', and Jentic returns the matching DialValet operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using DialValet API (current beta implementation) API through Jentic.

Is there a DialValet MCP server?

You don't need an MCP server to give your agent DialValet. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls the place-call, live-transcript, and steer operations. Operations are discovered on demand, so no extra server's tool definitions sit in the agent's context.

Can I limit what my agent is allowed to do with DialValet?

Yes. Write a rule that allows the place-call, live-transcript, and steer operations but not account deletion, API-key revocation, or billing checkout, so the agent can run and supervise calls while your account and wallet stay under your control, and every call it makes is logged.

What authentication does the DialValet API use?

Per its OpenAPI spec, the DialValet API accepts either a bearer key in the dv_live_ format in the Authorization header or a dv_session browser session cookie, and scoped bearer keys can be minted and revoked. A few operations need no credential, such as the health check and the OTP signup and sign-in steps. Placing a call additionally requires a verified caller ID, prepaid credit, and passing account limits. Through Jentic the key is stored encrypted by your own Jentic One instance and injected only at call time.

Can I place an outbound phone call with the DialValet API?

Yes. The place-call operation requests one outbound call to a number with a chosen GPT-Live voice, and you can then get its state and result, watch the live transcript, and cancel it if needed. The current beta is U.S.-only, and a call requires a verified caller ID and available prepaid credit.

What are the rate limits for the DialValet API?

The OpenAPI spec does not state numeric rate limits, but it enforces per-account limits and prepaid credit on placing calls; the policy operation reads the current safety limits and the balance operation reads available credit. Check dialvalet.com for current limits and the U.S.-only beta scope.

How do I place an AI phone call with the DialValet API through Jentic?

Verify a caller ID and confirm prepaid credit, then call the place-call operation with the number and voice and poll the call for its result. In Jentic, search for 'request an outbound AI phone call', store your API key once, and the agent runs the sequence. To run it on your own infrastructure, install Jentic One from its GitHub repo.

DialValet API (current beta implementation)

AI ReadinessAI-Aware (B+)67/100

See full scorecard

Official vendor OpenAPI document · agent-readyCommunicationsVoice Telephonybearer, apiKey37 EndpointsREST

For Agents

Request outbound phone calls voiced by a GPT-Live agent, watch the live transcript, and steer the agent mid-call. Handles caller-ID verification, prepaid billing, and transcripts across 37 endpoints.

Use for: Request an outbound call to a phone number with a chosen voice, Watch the live transcript of an in-progress call, Steer the live agent to correct what it is saying, Answer a question the live agent is asking mid-call

Not supported: Does not send SMS, email, or handle inbound calls, and the current beta is U.S.-only. Use for placing AI-voiced outbound phone calls only.

The DialValet API places outbound phone calls voiced by a GPT-Live agent: an agent requests one call to a number, picks a voice, and the platform dials and speaks. The call can be watched live as a streaming transcript, steered mid-call to correct the live agent, and paused to answer questions the agent raises before continuing. It also handles the surrounding account machinery: verified caller identities, a prepaid wallet with a ledger and Stripe checkout, and per-account safety limits, with structured call results and transcripts that can be retrieved or deleted. The current beta is U.S.-only.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: BSignals: 4

90%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

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.

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.

54%

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: B+Signals: 4

34%

Description Coverage

Coverage of descriptions across API elements.

86%

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

95%

OperationId Quality

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

54%

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: CSignals: 1

55%

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: C+Signals: 1

58%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the DialValet API (current beta implementation) to your agent

Capabilities

Start building with DialValet API (current beta implementation) API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

DialValet API (current beta implementation)

Jentic AI Readiness Score

DialValet API (current beta implementation)

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