---
title: "Connect Hume AI to Optimizely - APIANT.ai"
description: "When \"New Voice\" fires in Hume AI, your agent runs \"Add page\" in Optimizely. Describe the whole flow and it is built, tested on every scenario and kept running."
canonical: "https://apiant.ai/connect/hume-ai-to-optimizely"
---

# Connect Hume AI to Optimizely

When **New Voice** fires in [Hume AI](https://apiant.ai/connections/hume-ai), your agent runs **Add page** in [Optimizely](https://apiant.ai/connections/optimizely). Describe the whole flow and it is built, tested on every scenario and kept running.

Hume AI **4** triggers Hume AI **13** actions Optimizely **26** actions

What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.

## What do you want Hume AI and Optimizely to do together?

Give your AI client this address.

`https://mcp.apiant.ai`

One connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.

### Set it up in your client

### Claude Code

Run this in the directory you want to work in.

`claude mcp add --transport http -s project apiant-ai https://mcp.apiant.ai`

Start Claude Code there, approve the server, and sign in in the browser page it opens.

[Claude Code guide (opens in a new tab)](https://apiant.ai/docs/mcp/claude-code)

### Claude, web and desktop

Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Cursor

Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Zed

Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Codex and the ChatGPT desktop app

Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Any other MCP client

Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

Example flows

## What Hume AI can start in Optimizely

- When **New Voice** in Hume AI then **Add page** in Optimizely
- When **Chat ended (instant)** in Hume AI then **Add project** in Optimizely

Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.

Everything your agent can do with Hume AI and Optimizely

## Triggers and actions 4 triggers · 39 actions

- Trigger

**Chat ended (instant)**

Fires when an EVI chat session ends (chat_ended webhook event).

- Trigger

**Chat started (instant)**

Fires when a new EVI chat session begins (chat_started webhook event).

- Trigger

**New Voice**

Triggers when a new voice is created.

- Trigger

**Tool call (instant)**

Fires when EVI calls a registered tool during a conversation (tool_call webhook event).

- Action

**Add config**

Create a new EVI configuration (voice assistant setup).

- Action

**Add prompt**

Create a new system prompt for use in an EVI configuration.

- Action

**Add tool**

Create a new tool definition that EVI can call during a conversation.

- Action

**Add voice**

Save a new custom voice to the account from a TTS generation ID, for reuse in later speech requests.

- Action

**Convert voice**

Convert the speech in an uploaded audio file into a different saved voice.

- Action

**Delete config**

Delete an EVI configuration from the account.

- Action

**Delete voice**

Delete a saved custom voice from the account.

- Action

**Generate Text to Speech**

Convert text to speech using Hume AI's expressive text-to-speech technology.

- Action

**List configs**

List the EVI configurations saved to the account.

- Action

**List prompts**

List the prompts saved to the account.

- Action

**List tools**

List the tool definitions saved to the account.

- Action

**List voices**

List the custom voices saved to the account.

- Action

**Update config**

Update an EVI configuration's name or description.

- Action

**Add attribute**

Creates a new attribute in an Optimizely project, which can be used to target audiences.

- Action

**Add audience**

Adds a new audience to an Optimizely project and returns the id of the audience that was created.

- Action

**Add campaign**

Creates a new personalization campaign in an Optimizely project and returns its id.

- Action

**Add experiment**

Creates a new experiment in an Optimizely project and returns its id.

- Action

**Add feature**

Creates a new feature flag in an Optimizely project. Works only with legacy Full Stack projects, and returns the id of the new feature.

- Action

**Add page**

Creates a new page in an Optimizely project, defining the URL where experiments and campaigns can run and when it activates. Returns the created page.

- Action

**Add project**

Creates a new Optimizely project in your account and returns the created project.

- Action

**Delete experiment**

Archives an Optimizely experiment by its ID. Optimizely keeps archived experiments rather than permanently removing them.

- Action

**Get audience**

Returns a single Optimizely audience by its ID, including its name, targeting conditions and status. An error occurs if the audience is not found.

- Action

**Get campaign**

Returns a single Optimizely campaign by its ID, including its status, metrics, targeting and custom field values.

- Action

**Get experiment**

Returns a single experiment by its ID, including its status, variations, metrics and targeting. Fails if the experiment is not found.

- Action

**Get experiment results**

Returns the results of an Optimizely experiment, including metric performance per variation, reach and statistical significance, optionally limited to a time range or visitor segment.

- Action

**Get feature**

Returns a single feature by its ID, including its variables and its rollout rules in each environment. Works only with legacy Full Stack projects.

- Action

**Get project**

Returns all the properties of a single Optimizely project, including its platform, status and web snippet settings.

- Action

**List attributes**

Returns all attributes in an Optimizely project, including their keys, names and archived status.

- Action

**List audiences**

Returns the audiences in an Optimizely project, optionally filtered by archived or journey status.

- Action

**List campaigns**

Returns all campaigns in an Optimizely project, optionally narrowed by journey or archived status.

- Action

**List environments**

Returns all of the environments that have been created in an Optimizely project.

- Action

**List events**

Returns all events in an Optimizely project, including pageview events and, optionally, classic goals.

- Action

**List experiments**

Returns all experiments in an Optimizely project or campaign.

- Action

**List features**

Returns all features created in an Optimizely project, including their variables and per-environment rollout rules.

- Action

**List pages**

Returns the pages defined in an Optimizely project, optionally including single-use pages generated for campaign URL targeting.

- Action

**List projects**

Returns all the projects in your Optimizely account, with their settings and status.

- Action

**Update campaign**

Updates an existing Optimizely campaign's details, targeting and metrics, and can publish, start, pause, resume or unarchive it. Returns the updated campaign.

- Action

**Update experiment**

Updates an Optimizely experiment's settings, such as its name, audiences, metrics, variations and schedule, and can optionally publish, start, pause, resume or unarchive it. Returns the updated experiment.

- Action

**Update feature**

Updates an existing feature's name, key, description, variables, environment rollout rules or archived state, and returns the updated feature.

## Each app on its own

- [ **Hume AI** Hume AI is a platform for expressive AI interactions, that understands human emotions through voice and...](https://apiant.ai/connections/hume-ai)
- [ **Optimizely** The Optimizely platform technology provides A/B testing tools, in which two versions of a web page can be...](https://apiant.ai/connections/optimizely)

Reviews

## What our customers say

## More from Hume AI

- [ **Hume AI to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/hume-ai-to-salesforce)
- [ **Hume AI to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/hume-ai-to-slack)
- [ **Hume AI to Mailchimp** Mailchimp marketing automation and email platform.](https://apiant.ai/connect/hume-ai-to-mailchimp)
- [ **Hume AI to Stripe** Stripe is a payment processing platform for online businesses.](https://apiant.ai/connect/hume-ai-to-stripe)
- [ **Hume AI to Shopify** Shopify is a commerce platform for online stores and retail point-of-sale.](https://apiant.ai/connect/hume-ai-to-shopify)
- [ **Hume AI to QuickBooks Online** QuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...](https://apiant.ai/connect/hume-ai-to-quickbooks-online)

## More into Optimizely

- [ **HubSpot to Optimizely** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-optimizely)
- [ **Salesforce to Optimizely** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-optimizely)
- [ **Slack to Optimizely** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-optimizely)
- [ **Google Sheets to Optimizely** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-optimizely)
- [ **Gmail to Optimizely** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-optimizely)
- [ **Google Calendar to Optimizely** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-optimizely)

Questions

## Hume AI and Optimizely, answered

###

### What can start an automation from Hume AI?

Any of Hume AI's 4 triggers in the catalog, including New Voice, Chat ended (instant), Chat started (instant) and Tool call (instant). Describe the moment in plain language and your agent picks the right one.

###

### What can your agent do in Optimizely when something happens in Hume AI?

Any of Optimizely's 26 actions, including Update campaign, Update experiment, Update feature and Add attribute. Your agent maps the data both ways and tests every scenario before it ships.

###

### Can it also run from Optimizely to Hume AI?

Optimizely has no triggers in the catalog today, so automations start in Hume AI. If you need the other direction, ask: your agent reads Optimizely's API documentation and adds it.

###

### Do I have to build a connector for Hume AI or Optimizely?

No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.

###

### Can my AI client use Hume AI and Optimizely without building an automation?

Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.

###

### What happens when something fails?

Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.

###

### Is there a free plan?

Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.
