Opens calls with their cost and duration, changes assistant voice and model settings, provisions phone numbers, and runs call analytics.
42actions available
Every action runs live through MCP. Nothing to build, nothing to maintain.
Ayro creates a new voice or chat assistant with your chosen AI model, transcriber, and voice settings. Your team spins up specialized agents without touching infrastructure code.
Ayro retrieves the full details of a specific chat session to review how an interaction went. Your team audits calls for quality and uses transcripts to improve agent training.
Ayro adds documents to a Vapi knowledge base so agents can cite accurate, current information. Your team ensures every agent has access to the latest policies and FAQs.
Each card is one request a support team gets, and the Vapi actions Ayro runs to close it.
Ayro filters calls by assistant or phone number and opens the one in question with its status, duration, cost, and messages, so a complaint about a voice interaction is checked against the record.
Ayro creates an assistant with its transcriber, voice, and model configuration, adjusts those settings later, and uploads a file into the knowledge base the assistant draws its answers from.
Ayro provisions a number through Twilio, Vonage, Telnyx, Vapi, or a bring-your-own provider, changes which assistant it routes to, and releases it from the organization once it is no longer needed.
Ayro builds an eval with mock conversation messages to confirm the assistant answers correctly, defines the scorecard that grades its performance, and runs aggregated analytics across call and subscription metrics.
How it works
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Vapi actions it has and picks the ones a request needs.
Authorize the Vapi account your team already uses — one consent screen, no API keys, no mapping tables. Ayro can only do what you granted that account, and you can disconnect it at any time.
Describe the job the way you would hand it to a teammate. Ayro maps it to the Vapi actions that close it and chains as many as the request needs.
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started freeVapi · Ayro
What can you do in Vapi without me setting anything up?
These, right away:
Great, let's start with the first one.
FAQ
Setup, permissions, and the limits of what Ayro can do inside Vapi.
Yes, through monitoring policies. Create Monitoring Policy defines automated rules based on thresholds and time windows, and List Monitoring Policies returns what is already configured, so a spike in failed or costly calls surfaces without anyone sitting on the dashboard.
All 42 actions your agent can call on Vapi, straight from the live MCP connection.
Update an existing Vapi assistant configuration.
List calls from Vapi.
Delete a chat by its ID from Vapi.
Fetch chat details by ID.
Create and execute analytics queries on VAPI data.
Create a new Vapi assistant with specified transcriber, voice, and AI model configurations.
Create an eval for testing conversation flows.
Create an OpenAI-compatible chat using the Vapi API.
Create a phone number with Vapi.
Create a monitoring policy in VAPI.
Create an 11Labs pronunciation dictionary resource.
Create a scorecard for observability and evaluation.
Delete a call by its unique identifier.
Delete an eval by ID.
Delete a phone number from Vapi.
Retrieve an eval by its ID.
Delete an eval run by its ID from Vapi.
Update an existing eval in Vapi.
Retrieve a specific assistant by ID from Vapi.
Fetch call details by ID.
Retrieve a file by its ID from Vapi.
Retrieve insights from Vapi.
Retrieve monitoring policies from Vapi.
List observability scorecards with optional filtering and pagination.
List provider resources from Vapi.
List structured outputs with optional filtering.
Retrieve insights from VAPI.
List all assistants in your VAPI organization.
Retrieve a list of chat conversations from VAPI.
Retrieve a paginated list of evals from Vapi.
Same connection, same setup. Pick the next one your team already uses.
Lists the Claude models available on an account, retrieves one by ID, and sends a conversation history for a completion.
Creates agents and attaches sources, reindexes stale pages, reads traffic and conversation analytics, and scores individual answers for accuracy.
Runs OCR and image annotation over pictures and PDFs, builds the Product Search catalogue, and polls long-running batch operations.
Synthesizes speech in preset or custom voices, returns word-level timings for captions, and keeps the voice library and usage in check.
Finds models and reads their input schemas, runs and cancels predictions, manages deployments and hardware, and drives fine-tuning jobs.
Classifies incoming text into taxonomy categories, extracts named entities with confidence scores, and maintains the classifiers behind both.

Authorize the account and your agent has all 42 actions from the first conversation.
