--- title: "Connect EARLY to AssemblyAI - APIANT.ai" description: "When \"Activity Created\" fires in EARLY, your agent runs \"Upload file\" in AssemblyAI." canonical: "https://apiant.ai/connect/early-to-assemblyai" --- # Connect EARLY to AssemblyAI When **Activity Created** fires in [EARLY](https://apiant.ai/connections/early), your agent runs **Upload file** in [AssemblyAI](https://apiant.ai/connections/assemblyai). Describe the whole flow and it is built, tested on every scenario and kept running. EARLY **13** triggers EARLY **19** actions AssemblyAI **11** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want EARLY and AssemblyAI 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 EARLY can start in AssemblyAI - When **Activity Created** in EARLY then **Upload file** in AssemblyAI - When **Activity Updated** in EARLY then **Process Speech Understanding** in AssemblyAI 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 EARLY and AssemblyAI ## Triggers and actions 13 triggers · 30 actions - Trigger **Activity Created** Triggers when an activity is created. - Trigger **Activity Deleted** Triggers when an activity is deleted. - Trigger **Activity Updated** Triggers when an activity is updated. - Trigger **Folder Created** Triggers when a folder is created. - Trigger **Folder Deleted** Triggers when a folder is deleted. - Trigger **Folder Updated** Triggers when a folder is updated. - Trigger **Time Entry Created** Triggers when a time entry is created. - Trigger **Time Entry Deleted** Triggers when a time entry is deleted. - Trigger **Time Entry Updated** Triggers when a time entry is updated. - Trigger **Tracking Canceled** Triggers when a tracking is canceled. - Trigger **Tracking Started** Triggers when a new tracking is started. - Trigger **Tracking Stopped** Triggers when a tracking is stopped. - Trigger **Tracking Updated** Triggers when a tracking is updated. - Action **Add Member to Folder** Adds a person with a given email to a folder. - Action **Cancel Current Tracking** Cancels the tracking that is currently running without saving a time entry - Action **Create Activity** Creates an activity. - Action **Create Folder** Creates a folder. - Action **Create Tag** Creates an tag. - Action **Create Time Entry** Creates a time entry for a given activity, start- and end-time. - Action **Delete Activity** Deletes an activity by ID - Action **Delete Folder** Deletes a folder by ID - Action **Delete Time Entry** Deletes a time entry by ID - Action **Get Current Tracking** Gets the tracking that is currently running - Action **Get Folder** Gets a folder by ID - Action **Get Time Entry** Gets a time entry by ID - Action **List Activities** Lists the activities in the account - Action **Start Tracking** Start Tracking an Activity. - Action **Stop Current Tracking** Stop the current time tracking. - Action **Update Activity** Updates an existing activity by ID - Action **Update Current Tracking** Updates the tracking that is currently running - Action **Update Folder** Updates an existing folder by ID - Action **Update Time Entry** Updates an existing time entry by ID - Action **Delete Transcript** Deletes a transcript's data and marks it as deleted, along with any file uploaded for it. - Action **Get Paragraphs** Returns a completed transcript split into semantically segmented paragraphs, each with its text, timing, confidence and words. - Action **Get redacted audio** Returns the status and download URL of the PII-redacted audio for a transcript. Redacted audio files are available for 24 hours. - Action **Get Sentences** Returns a completed transcript split into sentences, with each sentence's text, timing, confidence, speaker and words. - Action **Get Transcript** Returns a transcript by its ID, including its status, text, words and any enabled audio-intelligence results. - Action **List transcripts** Returns the transcripts created in the last 30 days, newest first, optionally filtered by status or creation date (up to 200 per call). - Action **Process Speech Understanding** Runs a speech understanding task (translation, speaker identification, custom formatting, summarization or action items) on a completed transcript and returns the results. - Action **Prompt Transcript With LLM Gateway** Sends a prompt to an LLM through AssemblyAI's LLM Gateway, optionally injecting a transcript's text, and returns the model's response. - Action **Search Words** Searches a completed transcript for keywords or short phrases and returns each match with its count and timestamps. - Action **Transcribe** Submits an audio or video file at a public URL for transcription and returns the queued transcript, including its id and status. - Action **Upload file** Uploads an audio or video file to AssemblyAI and returns a private link you can use to transcribe it. ## Each app on its own - [ **EARLY** EARLY is a Time Tracking App: Effortless, Smart, and Secure.](https://apiant.ai/connections/early) - [ **AssemblyAI** Run speech-to-text and audio intelligence models from the AssemblyAI API.](https://apiant.ai/connections/assemblyai) Reviews ## What our customers say ## More from EARLY - [ **EARLY to Bugcrowd** Bugcrowd API for interacting and tracking the reported issues programmatically](https://apiant.ai/connect/early-to-bugcrowd) - [ **EARLY to Genshin Impact** The genshin.dev API serves reference game data for Genshin Impact.](https://apiant.ai/connect/early-to-genshin-impact) - [ **EARLY to Pipefile** Pipefile streamlines the collection of personal, financial, and otherwise sensitive documents to keep your...](https://apiant.ai/connect/early-to-pipefile) - [ **EARLY to Pulsedive** Scan, search and collect threat intelligence data in real-time](https://apiant.ai/connect/early-to-pulsedive) - [ **EARLY to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/early-to-salesforce) - [ **EARLY to Google Sheets** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/early-to-google-sheets) ## More into AssemblyAI - [ **HubSpot to AssemblyAI** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-assemblyai) - [ **Salesforce to AssemblyAI** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-assemblyai) - [ **Slack to AssemblyAI** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-assemblyai) - [ **Google Sheets to AssemblyAI** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-assemblyai) - [ **Gmail to AssemblyAI** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-assemblyai) - [ **Google Calendar to AssemblyAI** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-assemblyai) Questions ## EARLY and AssemblyAI, answered ### ### What can start an automation from EARLY? Any of EARLY's 13 triggers in the catalog, including Activity Created, Activity Updated, Folder Created and Folder Updated. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in AssemblyAI when something happens in EARLY? Any of AssemblyAI's 11 actions, including Upload file, Get Paragraphs, Get redacted audio and Get Sentences. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from AssemblyAI to EARLY? AssemblyAI has no triggers in the catalog today, so automations start in EARLY. If you need the other direction, ask: your agent reads AssemblyAI's API documentation and adds it. ### ### Do I have to build a connector for EARLY or AssemblyAI? 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 EARLY and AssemblyAI 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.