Configure AI Call Transcription with Google Service

Requirements

Yeastar P-Series Cloud Edition should meet the following requirements:

Prerequisites

PBX network access

Make sure the Yeastar P-Series Cloud Edition can access the following domains to use corresponding services:

Note:

You can verify domain accessibility on the PBX (Path: Maintenance > Troubleshooting > IP Ping).

Service	Domain
Google Cloud Speech-to-Text service	oauth2.googleapis.com <region>-speech.googleapis.com Note: Select the desired region from the list below and replace <region> with it (e.g., us-speech.googleapis.com). It is recommended to select a region closest to your PBX deployment location to reduce network latency and ensure stable transcription. us: United States eu: Europe asia-southeast1: Singapore asia-northeast1: Tokyo
GPT/Gemini LLM	According to your preferred LLM, the PBX must be able to access the following corresponding domains: GPT LLM: api.openai.com Gemini LLM: oauth2.googleapis.com and generativelanguage.googleapis.com

Third-party service account

You have prepared third-party service accounts and login credentials as follows:

Service	Account
Google Cloud Speech-to-Text service	Prepare a Google account with sufficient transcription minute quotas for Google Cloud Speech-to-Text service, and obtain the username and password.
GPT/Gemini LLM	According to your preferred LLM, the account must meet the following requirements: GPT LLM: Prepare an OpenAI account with sufficient token quota, and obtain the username and password. Gemini LLM: Make sure the Google account have sufficient token quota.

Procedure

• Step 1. Create an API key for Google Cloud Speech-to-Text service
• Step 2. (Optional) Create an API key for GPT LLM or Gemini LLM
• Step 3. Configure AI call transcription on the Yeastar PBX

Step 1. Create an API key for Google Cloud Speech-to-Text service

To securely access the Google Cloud Speech-to-Text service from the PBX, you must create an API key on Google Console first and export it as a JSON file used to authenticate the service API request.

1. Log in to Google Console using your Google username and password.
2. Create a new project.
   1. At the top-left corner, click current project tab, and then click New project in the pop-up window.

      

   2. In the New Project page, create a new project.

      

      1. In the Project name field, enter a name to identify the project.
      2. Optional: Click Browse to select the desired organization.
      3. Click Create.
3. In the new created project, enable the Cloud Speech-to-Text API service.

   

   1. Go to APIs & Services > Library, search for "Cloud Speech-to-Text API" in the library.
   2. In the search result list, click the Cloud Speech-to-Text API card to enter its product details.
   3. Click Enable.

      This service displays with Enabled status.

4. Create a service account for the new created project.
   1. Go to IAM & Admin > Service accounts, click Create service account at the top navigation bar.

      

   2. Create a service account.

      

      1. In the Service account name field, enter a name to identify the service account.
      2. Click Create and continue.
      3. In the Role drop-down list, select Owner.
      4. Click Continue.
      5. Click Done.

         The Service accounts list displays the created service account.

5. Create an API key and generate its JSON file for the new created service account.

   

   1. On the Service accounts page, click beside the created service account, and select Manage keys.
   2. On the Keys page, click Add key and select Create new key.

      A key type selection window pops up.

   3. In the Key type section, select JSON type, and click Create.

      The system automatically downloads the JSON file that contains the API key to your computer. You can check the JSON file on your computer and save it for later use.

Step 2. (Optional) Create an API key for GPT LLM or Gemini LLM

Yeastar P-Series Cloud Edition allows you to invoke APIs of GPT or Gemini LLM to automatically generate call summaries from transcribed text after calls end. To implement this feature, you need to create an API key to authenticate requests.

• If you use GPT LLM provided by OpenAI, proceed with Create an API key for OpenAI API.
• If you use Gemini LLM provided by Google, proceed with Create an API key for Gemini API.

Create an OpenAI API key on OpenAI Platform

1. Log in to OpenAI Platform using your OpenAI username and password, go to API Keys.
2. At the top-right corner of the API key list, click Create new secret key.
3. In the pop-up window, create a new API key.

   

   1. In the Name field, enter a name to identify the API key.
   2. In the Project drop-down list, select the desired project.
   3. Keep the default All permission, and click Create secret key.

      A pop-up window appears, displaying the generated API key.

      

   4. In the pop-up window, click Copy to copy the API key and save it for later use.

Create a Gemini API key on Google AI Studio

1. Log in to Google AI Studio using your Google username and password, go to Dashboard > API keys.
2. At the top-right corner of the API key list, click Create API key.
3. In the pop-up window, create a new API key.

   

   1. In the Name your key field, enter a name to identify the API key.
   2. In the Choose an imported project drop-down list, select a desired project.
      Note: In the drop-down list, you can select an existing project, import a project, or create a new one as needed.
   3. Click Create key.

      A pop-up window appears, displaying the details of the generated API key.

      

   4. In the pop-up window, click Copy key to copy the API key and save it for later use.

Step 3. Configure AI call transcription on the Yeastar PBX

After you create authentication credentials for Google Cloud Speech-to-Text service and LLM, you need to configure corresponding settings on the PBX to establish connections between the PBX and the two services.

1. Log in to PBX web portal, go to AI > AI Toolbox.
2. Turn on the switch of Call Transcription.
3. Configure AI call transcription service.

   

   1. In the Service Type drop-down list, select Custom Service.
   2. In the Transcription Service Provider drop-down list, select Google.
   3. Click Browse to upload the API key JSON file.
   4. In the Region drop-down list, select the desired region.
      • us (multi-region): United States
      • eu (multi-region): Europe
      • asia-southeast1: Singapore
      • asia-northeast1: Tokyo

   5. Configure the LLM service.

      Option	Instruction
      Disable	If you do not need the PBX to generate call summaries, select Disable in the LLM Provider drop-down list.
      OpenAI	To use GPT LLM, complete the following settings: In the LLM Provider drop-down list, select OpenAI. In the API key field, paste the API key created on OpenAI Platform. In the GPT Model field, enter the model ID of your preferred GPT LLM. Note: You can access the list of GPT Models to check the model ID of your desired GPT LLM. For example, if you want to use GPT-5.4, enter the model ID gpt-5.4 in this field.
      Google	To use Gemini LLM, complete the following settings: In the LLM Provider drop-down list, select Google. In the API key field, paste the API key created on Google AI Studio. In the Gemini Model field, enter the model code of your preferred Gemini LLM. Note: You can access the list of Gemini Models and go to introduction page of your desired Gemini LLM to check its model code. For example, if you want to use Gemini 3.1 Pro Preview, enter the model code gemini-3.1-pro-preview in this field.

4. In the Language drop-down list, select the desired language to be detected and transcribed for call audio.

5. In the Extension Scope for This Feature section, specify which extensions / extension groups / departments have access to the call transcription feature.
   • All Extensions: All extensions can use this feature.
   • Specific Extensions: Only selected extensions can use this feature.
6. Click Save.

Result

• The Transcription Connection Status displays Enable, indicating that the AI call transcription feature powered by Google Cloud Speech-to-Text service is enabled. Call audio can be detected and transcribed into readable text in the specified language in real time via the Google service.

  

  Note: You can configure the call transcription language and mode (either automatic or manual) for extensions individually as needed (Path: Extension and Trunk > Extension > AI > Call Transcription). For more information, see Configure AI Call Transcription for an Extension.

• The LLM Connection Status displays Enable, indicating that the PBX is successfully connected to the configured LLM. The PBX will automatically generate call summaries from transcribed text after calls end via the LLM.