Itsconvo Convo API
69
AI ReadinessAI-Aware (B+)69/100
Official vendor OpenAPI document · agent-readyProductivityNote Takingbearer20 EndpointsREST
For Agents
Read recorded sales-call transcripts and key points from Convo, ask questions about a call, generate coaching feedback and follow-up emails, and pull contact briefings and open action items before the next meeting.
Use for: Find the call where we discussed pricing with Acme, Get the transcript of yesterday's sales call, I need a follow-up email for Sarah from this call, Retrieve coaching feedback on my last demo
Not supported: Does not record calls itself, send emails, or manage CRM deals. Use for reading and acting on calls recorded by the Convo desktop app only.
The Convo API gives your code the sales calls the Convo desktop app records: transcripts, key points, coaching feedback, and answers to questions about a single call. It drafts follow-up emails in a professional, casual, or concise tone, shares a call by link, renames or deletes it, and lists upcoming events from the connected Google or Outlook calendar. On Professional and Enterprise plans, Convo Memory adds contact lists, open action items from past meetings, and pre-call briefings, and webhooks report events such as transcript.ready and conversation.feedback.ready.
Install Jentic One Beta
Connect the Convo API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Convo 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%2Fitsconvo.com%2Fitsconvo" | 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%2Fitsconvo.com%2Fitsconvo" | 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 Convo API.
Search recorded calls by title or transcript words and read a call's transcript oldest segment first
Generate or read the key points and coaching feedback for a call, with forceRefresh to regenerate them
Ask a question about one call and get an answer drawn from its transcript
Draft a follow-up email from a call for a recipientName in a professional, casual, or concise tone
Pull a Convo Memory briefing on a contact with relationship summary, recent meetings, open action items, and decisions
Register HTTPS webhooks for events such as transcript.ready and conversation.keypoints.ready, and send a signed test event
Use Cases
Patterns agents use Convo API for, with concrete tasks.
★ Agent-drafted call follow-ups
An AI agent acting as a sales assistant turns each recorded call into a follow-up without the rep copying notes. Through Jentic the agent searches for 'draft a follow-up email from a call', finds the latest conversation, reads its key points, and asks Convo to draft the email for the named recipient, with the convo_ key injected at call time. Each email draft uses one AI credit, so the agent only drafts for calls that need a reply.
Call GET /api/v1/conversations with limit 1, then POST /api/v1/conversations/{id}/keypoints and POST /api/v1/conversations/{id}/email with recipientName Sarah and tone concise for that call
Pre-call briefing
Before a meeting, a rep wants to know what was said last time and what is still open. Convo Memory returns a briefing on one contact with the relationship summary, recent meetings, open action items, and recent decisions, and the unresolved-threads read lists open action items across contacts, oldest meeting first. Both need a Professional or Enterprise plan with Memory enabled.
Call GET /api/v1/calendar/events with maxResults 5, match the next attendee in GET /api/v1/contacts with search, and call GET /api/v1/contacts/{id}/briefing for that contact
Sales coaching review
A sales manager reviewing a rep's week reads coaching feedback on each call and asks targeted questions about objections. Feedback generation uses one AI credit and needs at least 10 transcript segments, and the query operation answers a question from one call's transcript with suggested follow-up questions.
Call POST /api/v1/conversations/{id}/feedback for a call, then POST /api/v1/conversations/{id}/query with query What objections did the prospect raise?
Pushing call events into other tools
A team syncing calls into its CRM registers a webhook so new transcripts arrive without polling. Webhooks take an HTTPS url and a list of events such as transcript.ready or conversation.action_items.ready, the secret is returned once at creation, and the test operation sends a signed webhook.test event and reports the receiving server's status code.
Call POST /api/v1/webhooks with url https://hooks.example.com/convo and events transcript.ready and conversation.keypoints.ready, then POST /api/v1/webhooks/test with the returned webhookId
Key Endpoints
20 endpoints — the convo api gives your code the sales calls the convo desktop app records: transcripts, key points, coaching feedback, and answers to questions about a single call.
METHOD
PATH
DESCRIPTION
GET
/api/v1/conversations
List and search conversations
GET
/api/v1/conversations/{id}/transcript
Get a transcript
POST
/api/v1/conversations/{id}/keypoints
Generate key points
POST
/api/v1/conversations/{id}/query
Ask a question about a call
POST
/api/v1/conversations/{id}/email
Draft a follow-up email
GET
/api/v1/contacts/{id}/briefing
Get a contact briefing
POST
/api/v1/webhooks
Register a webhook
GET
/api/v1/conversations
List and search conversations
GET
/api/v1/conversations/{id}/transcript
Get a transcript
POST
/api/v1/conversations/{id}/keypoints
Generate key points
POST
/api/v1/conversations/{id}/query
Ask a question about a call
POST
/api/v1/conversations/{id}/email
Draft a follow-up email
GET
/api/v1/contacts/{id}/briefing
Get a contact briefing
POST
/api/v1/webhooks
Register a webhook
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.
C
Convo API
- AI-Aware (B+)69/100
90
Foundational Compliance68
Developer Experience & Jentic Compatibility52
AI-Readiness & Agent Experience94
Agent Usability60
Security79
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
90
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: ASignals: 4
98%
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).
60%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
68
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B+Signals: 4
21%
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.
52
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: C-Signals: 4
49%
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.
57%
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).
79
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A-Signals: 1
79%
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 Convo by hand means creating a convo_ key in the desktop app, sending it as a bearer token, and handling hourly 429 limits and plan-gated routes like webhooks and Convo Memory. Through Jentic you install once, import Convo from the API Directory, store the key once, and your agent calls it.
Permission scoping
Convo puts the conversation id in the URL path (/api/v1/conversations/{id}/...), so a rule can scope your agent to one call. You choose the operations it may call, so actions like DELETE /api/v1/conversations/{id} or sharing a call by link are not included unless you add them.
Credential isolation
Your Convo 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 'get a sales call transcript' or 'draft a follow-up email', and Jentic returns the matching Convo operation with its input schema so the agent calls the right endpoint.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Convo API through Jentic.
What authentication does the Convo API use?
Per its OpenAPI spec, every operation takes a bearer token: Authorization: Bearer with a convo_ key created in the Convo desktop app under Settings, Convo API. Keys work on Starter, Professional, and Enterprise plans. Through Jentic the key is stored by your own instance and attached at call time, so the agent never sees it.
What are the rate limits for the Convo API?
The spec lists hourly limits by plan: 100 requests per hour on Starter, 500 on Professional, and 2,000 on Enterprise. Over the limit you get 429 rate_limited with Retry-After, and successful responses carry X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset. See https://docs.itsconvo.com/tiers for plan details.
Which Convo API calls use AI credits?
Per the spec, generating coaching feedback, querying a call, and drafting a follow-up email each use one AI credit, while generating key points does not. GET /api/v1/user/profile returns how many AI credits you have used this month.
Is there a Convo MCP server?
You don't need an MCP server to give your agent Convo. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the conversation, contact, and webhook operations it needs without loading another server's tool definitions into its context.
Can I limit what my agent is allowed to do with the Convo API?
Yes. For example, write a rule that allows only the transcript and keypoints reads under /api/v1/conversations/{id}/ plus the conversation list, and the agent can read your calls but cannot share them by link, rename them, or delete them. Every call it makes is logged.
How do I get a call transcript through Jentic?
Search Jentic for 'get a sales call transcript', load GET /api/v1/conversations to find the call by search term, then load GET /api/v1/conversations/{id}/transcript and execute it with that call's id. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED