# Zapier integration Transcribe audio in your Zapier workflow - no code required. The Speechmatics Zapier integration is currently in beta. Features and behavior may change. [Zapier](https://zapier.com) is a no-code automation platform that connects thousands of apps — including Speechmatics — into automated workflows. This guide walks you through adding Speechmatics as an action in your Zaps. ## Before you begin[​](#before-you-begin "Direct link to Before you begin") To build a Speechmatics Zap, you'll need: * A Speechmatics API key from the [Speechmatics portal](https://portal.speechmatics.com). * A [Zapier account](https://zapier.com). ## Create a Zap[​](#create-a-zap "Direct link to Create a Zap") Sign in to your [Zap dashboard](https://zapier.com/app/assets/zaps) and click **Create** to open a blank Zap in the editor. This is where you build workflows by adding a trigger and chaining actions. You should see something like this: ![Zapier dashboard with the Create button highlighted, ready to open a new blank Zap in the editor](/img/integrations/zapier-creating-zap.png) ### Set up a trigger[​](#set-up-a-trigger "Direct link to Set up a trigger") Zaps are made up of **triggers** and **actions**. The **trigger** is the event that starts your Zap. Pick the app you want to trigger from — this example trigger runs when a new file is shared in Slack. ![Zapier editor showing a Slack "new file" trigger connected to the Speechmatics Get Transcript from Audio action](/img/integrations/zapier-example.png) Zapier might prompt you to sign in when connecting certain apps. Some apps need additional account permissions before they can run in your Zap. ### Add Speechmatics to your Zap[​](#add-speechmatics-to-your-zap "Direct link to Add Speechmatics to your Zap") Next, set up your **actions** — the events that run after your trigger fires. Speechmatics provides two actions in Zapier: | Action | What it does | Best for | | ----------------------------- | ---------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- | | **Get Transcript from Audio** | Sends audio to Speechmatics and returns the transcript inside the Zap. | Short audio. Keeping the transcript in Zapier. | | **Submit Audio (Webhook)** | Sends audio to Speechmatics and delivers the finished transcript to a webhook URL you provide. | Longer recordings. Sending transcript to another system asynchronously. | For simplicity, this example uses **Get Transcript from Audio**. Click the Action box and search for Speechmatics. You should see the following menu: ![Zapier editor showing the Speechmatics app menu with the two available actions](/img/integrations/zapier-speechmatics-menu.png) Choose **Get Transcript from Audio** as the action, then connect your Speechmatics account by pasting your API key into the Account section. ### Configure transcription settings[​](#configure-transcription-settings "Direct link to Configure transcription settings") Click on the **Configure** tab. You should see something like this: ![Zapier editor showing the Configure tab for the Speechmatics Get Transcript from Audio action](/img/integrations/zapier-configure.png) Each **trigger** has **fields** you can connect to your action. Connect the trigger's file URL to the **Audio URL** field on the Speechmatics action. Depending on the trigger app, that URL might be called something like `/file` or `/url` — you may need to experiment to find it. Then configure your transcript output using these settings: | Setting | What it does | Learn more | | ----------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------- | | **Language hints** | **Optional.** Speechmatics auto-detects the language by default. Use hints to narrow detection to specific languages — search the dropdown by name, or type a language code. | [Languages](/speech-to-text/languages.md) | | **Speaker diarization** | Separates the transcript by speaker. | [Speaker diarization](/speech-to-text/features/diarization.md) | | **Output format** | Controls the shape of the returned transcript. | [Output formats](/speech-to-text/batch/output.md) | Once you've configured your settings, click the **Test** tab, then click **Test Step**. Zapier validates your configuration and runs it. ![Zapier editor showing a successful Test Step result for the Speechmatics Get Transcript from Audio action](/img/integrations/zapier-test-complete.png) When test succeeds, click **Publish** — your Zap is now live. ## Troubleshooting[​](#troubleshooting "Direct link to Troubleshooting") | Problem | What to try | | ------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **You can't sign in to Speechmatics** | Sign out from the Speechmatics account dropdown, then sign in again. If that fails, verify your login details in the [Speechmatics portal](https://portal.speechmatics.com). | | **Your API key isn't accepted** | Check that your account has credits in the usage and billing section of the [Speechmatics portal](https://portal.speechmatics.com). | | **You can't find the right field for Audio URL** | Field paths start with `/` — Zapier uses this to map fields between triggers and actions. Names vary by app; try `/file`, `/url`, or similar. | | **Your test step keeps failing** | Confirm you're passing an audio file, not another file type. To rule out a file problem, test with this [sample audio file](https://github.com/speechmatics/speechmatics-js-sdk/raw/7d219bfee9166736e6aa21598535a194387b84be/examples/nodejs/example.wav). | Still stuck? See [Zapier support](https://help.zapier.com/hc/en-us) or [contact Speechmatics](https://www.speechmatics.com/company/contact). ## Next steps[​](#next-steps "Direct link to Next steps") * [Explore all supported languages](/speech-to-text/languages.md) * [Configure speaker diarization](/speech-to-text/features/diarization.md) * [Choose an output format](/speech-to-text/batch/output.md) * [Learn what the Batch API supports](/speech-to-text/batch/quickstart.md)