--- title: "Connect Speak Ai to AssemblyAI - APIANT.ai" description: "When \"New Magic Prompts Response\" fires in Speak Ai, your agent runs \"Prompt Transcript With LLM Gateway\" in AssemblyAI." canonical: "https://apiant.ai/connect/speak-ai-to-assemblyai" --- # Connect Speak Ai to AssemblyAI When **New Magic Prompts Response** fires in [Speak Ai](https://apiant.ai/connections/speak-ai), your agent runs **Prompt Transcript With LLM Gateway** in [AssemblyAI](https://apiant.ai/connections/assemblyai). Describe the whole flow and it is built, tested on every scenario and kept running. Speak Ai **1** trigger Speak Ai **23** 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 Speak Ai 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 Speak Ai can start in AssemblyAI - When **New Magic Prompts Response** in Speak Ai then **Prompt Transcript With LLM Gateway** in AssemblyAI - When **New Magic Prompts Response** in Speak Ai then **Upload file** 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 Speak Ai and AssemblyAI ## Triggers and actions 1 trigger · 34 actions - Trigger **New Magic Prompts Response** Fires when Speak AI finishes answering an AI Chat (Magic Prompt) and delivers the final answer. - Action **Add Automation** Create a new Speak AI automation. - Action **Add Field** Creates a new custom field in your Speak AI account. - Action **Add Folder** Create a new folder to organize media, text notes, and recordings. - Action **Ask AI Chat** Ask a question about one or more media items or a folder and get the AI chat answer back. - Action **Delete Automation** Delete an automation. - Action **Delete Folder** Delete a folder. - Action **Delete Media** Delete a media file from Speak AI. - Action **Delete Text Note** Delete a text note. - Action **Get Media Insights** Loads the analysis results (transcript, keywords, topics, sentiment, named entities, summary) for a Speak AI audio or video file. - Action **Get Media Status** Gets the processing status and basic details of a Speak AI audio or video file. - Action **Get Media Transcript** Get the transcript of a media file. - Action **Get Text Note Insight** Gets the analysis insights (keywords, entities, intents, sentiment) for a Speak AI text note. - Action **List Automations** List the automations (trigger + action workflows) configured in Speak AI. - Action **List Fields** Lists the custom fields defined in your Speak AI account. - Action **List Folders** List the folders in the account. - Action **List Media** List the media files (audio/video) in the account's Speak AI library. - Action **Run Magic Prompt** Runs a Magic Prompt (Speak AI's AI Chat) against your media, folders or fields and returns the AI's answer. - Action **Update Automation** Updates an existing Speak AI automation: its name, trigger, steps, schedule and active state. - Action **Update Folder** Update a folder's name or settings. - Action **Update Media** Rename a Speak AI media file and update its description, tags, folder, assignee, note, status or creation date. - Action **Update Text Note** Update the content of an existing text note. - Action **Upload File to Transcribe and Analyze** Uploads new audio or video files for automatic transcription and analysis. - Action **Upload Text Note to Analyze** Uploads new text notes for automatic insight analysis. - 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 - [ **Speak Ai** Speak Ai is a tool to analyze audio and video to get insights extraction and transcriptions.](https://apiant.ai/connections/speak-ai) - [ **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 Speak Ai - [ **Speak Ai to Bugcrowd** Bugcrowd API for interacting and tracking the reported issues programmatically](https://apiant.ai/connect/speak-ai-to-bugcrowd) - [ **Speak Ai to Stripe** Stripe is a payment processing platform for online businesses.](https://apiant.ai/connect/speak-ai-to-stripe) - [ **Speak Ai to Trello** Trello is a visual collaboration tool that organizes projects into boards, lists, and cards.](https://apiant.ai/connect/speak-ai-to-trello) - [ **Speak Ai to Zoom** Zoom unifies cloud video conferencing, simple online meetings, group messaging, and a software-based...](https://apiant.ai/connect/speak-ai-to-zoom) - [ **Speak Ai to Twilio** Cloud communications platform for sending SMS/MMS messages, making and managing voice calls, and looking up...](https://apiant.ai/connect/speak-ai-to-twilio) - [ **Speak Ai to Typeform** Build and publish online forms, surveys, and quizzes with Typeform.](https://apiant.ai/connect/speak-ai-to-typeform) ## 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 ## Speak Ai and AssemblyAI, answered ### ### What can start an automation from Speak Ai? Any of Speak Ai's 1 trigger in the catalog, including New Magic Prompts Response. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in AssemblyAI when something happens in Speak Ai? 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 Speak Ai? AssemblyAI has no triggers in the catalog today, so automations start in Speak Ai. 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 Speak Ai 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 Speak Ai 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.