Integration

Google Speech-to-Text integration

Google Cloud Speech-to-Text API for converting audio to text using machine learning. Supports synchronous and asynchronous (long-running) recognition, streaming, custom vocabulary, speaker diarization, and 125+ languages.

Connect Google Speech-to-Text How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Google Speech-to-Text.Built from the 21 Google Speech-to-Text tools below, on the connection you add once.

Common Google Speech-to-Text use cases

automate recognizer management
automate phrase set management
automate custom class management
automate operation management
automate config management
automate recognize management
get config programmatically
get operation programmatically
update config programmatically
get phrase set programmatically

What you can do with Google Speech-to-Text

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Recognizer, 6 operations

create_recognizerCreate recognizerPOSTCreates a new recognizer resource with custom configuration for speech recognition. The recognizer stores default recognition settings that can be reused across requests.
delete_recognizerDelete recognizerDELETESoft-deletes a recognizer. The recognizer can be recovered using UndeleteRecognizer within a retention window.
get_recognizerGet recognizerGETGets the details of a specific recognizer resource.
list_recognizersList recognizersGETLists recognizers in a project and location. Returns a paginated list of recognizer resources.
undelete_recognizerUndelete recognizerPOSTUndeletes a previously soft-deleted recognizer. The recognizer can be recovered within a retention window after deletion.
update_recognizerUpdate recognizerPATCHUpdates an existing recognizer's configuration. Use the updateMask to specify which fields to update.

Custom class, 4 operations

create_custom_classCreate custom classPOSTCreates a new custom class resource. Custom classes contain domain-specific words and phrases to boost recognition accuracy in phrase sets.
delete_custom_classDelete custom classDELETESoft-deletes a custom class resource. The custom class can be recovered using UndeleteCustomClass within the retention window.
get_custom_classGet custom classGETGets the details of a specific custom class resource. Custom classes contain domain-specific words and phrases to improve recognition accuracy.
list_custom_classesList custom classesGETLists all custom classes in a project and location. Custom classes allow you to specify a set of words or phrases that the model should recognize with particular attention.

Phrase set, 4 operations

create_phrase_setCreate phrase setPOSTCreates a new phrase set resource. Phrase sets boost the recognition likelihood for specific words and phrases, improving accuracy for domain-specific vocabulary.
delete_phrase_setDelete phrase setDELETESoft-deletes a phrase set resource. The phrase set can be recovered within the retention window.
get_phrase_setGet phrase setGETGets the details of a specific phrase set resource.
list_phrase_setsList phrase setsGETLists all phrase sets in a project and location. Phrase sets specify a list of phrases and boost values to improve recognition accuracy for specific terms.

Operation, 3 operations

cancel_operationCancel operationPOSTStarts asynchronous cancellation of a long-running operation. The server makes a best effort to cancel the operation but success is not guaranteed.
get_operationGet operationGETGets the latest state of a long-running operation. Use this to poll the result of an async operation such as batchRecognize.
list_operationsList operationsGETLists long-running operations for a project and location. Operations are created by batchRecognize and other async methods.

Config, 2 operations

get_configGet configGETGets the project-level configuration for Speech-to-Text, including default settings and encryption configuration.
update_configUpdate configPATCHUpdates the project-level configuration for Speech-to-Text, such as the default KMS encryption key.

Recognize, 2 operations

batch_recognizeBatch recognizePOSTPerforms asynchronous batch speech recognition on a list of audio files stored in Google Cloud Storage. Returns a long-running operation. Suitable for large volumes of audio.
recognizeRecognizePOSTPerforms synchronous speech recognition on audio data. Returns results after the audio has been processed. Suitable for short audio files up to 60 seconds.

OAuth scopes Google Speech-to-Text requires

Each operation declares the scopes Google Speech-to-Text requires for it.

https://www.googleapis.com/auth/cloud-platformneeded by batch_recognize, cancel_operation, create_custom_class and 18 more

Use Google Speech-to-Text from Claude Code, Cursor or Codex

Connect Google Speech-to-Text in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Google Speech-to-Text operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Google Speech-to-Text

Create your workspace
Sign up free. Nothing to install.
Connect Google Speech-to-Text once
Add your Google Speech-to-Text connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Google Speech-to-Text integration FAQ

What can you do with the Google Speech-to-Text integration?

LiveContext exposes 21 operations on Google Speech-to-Text, covering recognizer, custom class, phrase set and operation. Common uses include automate recognizer management, automate phrase set management and automate custom class management.

Which OAuth scopes does Google Speech-to-Text require?

The operations that declare a scope all need https://www.googleapis.com/auth/cloud-platform.