This document contains current API restrictions and usage limits on use of the Speech API. This page will be updated to reflect any changes to these restrictions and usage limits. We reserve the right to change these limits.
Content to the Speech API is provided as audio data, either directly within
content field of the request or referenced within a Google Cloud Storage
URI in the
uri field of the request.
The API contains the following limits on the size of this content (and are subject to change):
|Content Limit||Audio Length|
|Synchronous Requests||~1 Minute|
|Asynchronous Requests||~180 Minutes*|
|Streaming Requests||~1 Minute|
* Audio longer than ~1 minute must use the
uri field to reference an audio file in Google Cloud Storage.
StreamingRecognize requests, audio must be sent at a rate that
approximates real time.
Attempting to process content in excess of these content limits will produce an error.
Within any request, you may also supply a SpeechContext, containing a list of phrases specific to the request. (A single words counts as a phrase in this context.) The following limits apply to such a context:
|Phrases per request||500|
|Total characters per request||10,000|
|Characters per phrase||100|
The current API usage limits for the Cloud Speech API are as follows (and are subject to change):
|Type of Limit||Usage Limit|
|Requests per 100 seconds*||500|
|Requests per day*||250,000|
|Processing per 100 seconds||10,800 seconds of audio|
|Processing per day||480 hours of audio|
StreamingRecognize session is considered a single request even though
it includes multiple frames of
StreamingRecognizeRequest audio within the
Requests and/or attempts at audio processing in excess of these limits will produce an error.
These limits apply to each Cloud Speech API developer project, and are shared across all applications and IP addresses using a given a developer project.