--- title: "Connect Langfuse and Speak Ai - APIANT.ai" description: "When \"New Trace\" fires in Langfuse, your agent runs \"Update Text Note\" in Speak Ai, or \"New Magic Prompts Response\" in Speak Ai to \"Add Prompt\" in Langfuse." canonical: "https://apiant.ai/connect/langfuse-to-speak-ai" --- # Connect Langfuse and Speak Ai When **New Trace** fires in [Langfuse](https://apiant.ai/connections/langfuse), your agent runs **Update Text Note** in [Speak Ai](https://apiant.ai/connections/speak-ai), or **New Magic Prompts Response** in Speak Ai to **Add Prompt** in Langfuse. Describe the whole flow and it is built, tested on every scenario and kept running. Langfuse **1** trigger Langfuse **14** actions Speak Ai **1** trigger Speak Ai **23** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want Langfuse and Speak Ai 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 Langfuse and Speak Ai can do together ### From Langfuse to Speak Ai - When **New Trace** in Langfuse then **Update Text Note** in Speak Ai - When **New Trace** in Langfuse then **Upload File to Transcribe and Analyze** in Speak Ai ### From Speak Ai to Langfuse - When **New Magic Prompts Response** in Speak Ai then **Add Prompt** in Langfuse - When **New Magic Prompts Response** in Speak Ai then **Get Prompt** in Langfuse 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 Langfuse and Speak Ai ## Triggers and actions 2 triggers · 37 actions - Trigger **New Trace** Polling trigger: fires for newly created traces (dedup by trace id / timestamp). - Action **Add Comment** Add a comment to a trace/observation/session/prompt object. - Action **Add Dataset** Create a new dataset. - Action **Add Dataset Item** Create an item (input/expected_output/metadata) in a dataset. - Action **Add Prompt** Create a new prompt version (text or chat). - Action **Add Score** Create a score attached to a trace/observation/session (numeric, categorical, or boolean). - Action **Delete Trace** Delete a trace by id. - Action **Get Project** Reads the Langfuse project that the connection's project-scoped API key belongs to. - Action **Get Prompt** Get a prompt by name (and optional version/label). - Action **Get Trace** Get a single trace by id, including nested observations/scores. - Action **List Dataset Items** List items in a dataset. - Action **List Datasets** List all datasets in the project. - Action **List Prompts** List all prompts in the project. - Action **List Scores** List scores with optional filters. - Action **List Traces** List traces with optional filters (user, session, tags, timerange). - 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. ## Each app on its own - [ **Langfuse** Langfuse is an open-source LLM engineering platform (GitHub) that helps teams collaboratively debug...](https://apiant.ai/connections/langfuse) - [ **Speak Ai** Speak Ai is a tool to analyze audio and video to get insights extraction and transcriptions.](https://apiant.ai/connections/speak-ai) Reviews ## What our customers say ## More from Langfuse - [ **Langfuse to 5DollarFootball** Football fixtures, results, standings and historical odds with corner and card lines](https://apiant.ai/connect/langfuse-to-5dollarfootball) - [ **Langfuse to Cloudflare Trace** Cloudflare Trace is a free JSON wrapper over Cloudflare's edge trace endpoint that reports what Cloudflare...](https://apiant.ai/connect/langfuse-to-cloudflare-trace) - [ **Langfuse to PaperClean** Clean document photos for printing, remove shadows, fix lighting](https://apiant.ai/connect/langfuse-to-paperclean) - [ **Langfuse to Postman** Postman is a platform for building and testing APIs.](https://apiant.ai/connect/langfuse-to-postman) - [ **Langfuse to Rendobar** Hosted media processing over REST: transcode, caption, watermark video](https://apiant.ai/connect/langfuse-to-rendobar) - [ **Langfuse to Runpod** Cloud GPU platform for renting on-demand compute to train and deploy AI models, including serverless...](https://apiant.ai/connect/langfuse-to-runpod) ## More into Speak Ai - [ **HubSpot to Speak Ai** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-speak-ai) - [ **Salesforce to Speak Ai** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-speak-ai) - [ **Slack to Speak Ai** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-speak-ai) - [ **Google Sheets to Speak Ai** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-speak-ai) - [ **Gmail to Speak Ai** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-speak-ai) - [ **Google Calendar to Speak Ai** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-speak-ai) Questions ## Langfuse and Speak Ai, answered ### ### What can start an automation from Langfuse? Any of Langfuse's 1 trigger in the catalog, including New Trace. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Speak Ai when something happens in Langfuse? Any of Speak Ai's 23 actions, including Update Automation, Update Folder, Update Media and Update Text Note. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Speak Ai to Langfuse? Yes. When something happens in Speak Ai, your agent can act in Langfuse too. This page covers both directions: Speak Ai's triggers and Langfuse's actions are listed here as well. ### ### Do I have to build a connector for Langfuse or Speak Ai? 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 Langfuse and Speak Ai 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.