Updated
Integrate Google ASR into Conversational AI Engine.
Google provides advanced automatic speech recognition with high accuracy and support for multiple languages, designed for real-time conversational AI applications.
Info
This integration is fully supported for use with Conversational AI Engine. While it has completed functional validation, it is newer to the platform, and additional provider-specific edge cases may be identified as usage scales across a broader range of applications and workloads.
Sample configuration
The following example shows how to configure Google ASR when starting a conversational AI agent.
from agora_agent import Agent, GoogleSTT
# client is your configured Agora client
agent = (
Agent(client)
.with_stt(GoogleSTT(
project_id='your-google-project-id',
location='global',
adc_credentials_string='your-google-credentials-json-string',
language='en-US',
model='long',
))
.with_llm(...) # configure your LLM vendor
.with_tts(...) # configure your TTS vendor
)import { Agent, GoogleSTT } from 'agora-agents';
// client is your configured Agora client
const agent = new Agent({ client })
.withStt(new GoogleSTT({
projectId: 'your-google-project-id',
location: 'global',
adcCredentialsString: 'your-google-credentials-json-string',
language: 'en-US',
model: 'long',
}))
.withLlm(/* configure your LLM vendor */)
.withTts(/* configure your TTS vendor */);import "github.com/AgoraIO/agora-agents-go/v2/agentkit/vendors"
// client is your configured Agora client
agent := agentkit.NewAgent(client).WithStt(
vendors.NewGoogleSTT(vendors.GoogleSTTOptions{
ProjectID: "your-google-project-id",
Location: "global",
ADCCredentialsString: "your-google-credentials-json-string",
Language: "en-US",
Model: "long",
}),
).WithLlm(/* configure your LLM vendor */).
WithTts(/* configure your TTS vendor */)Use the following asr configuration in your request:
"asr": {
"vendor": "google",
"language": "en-US",
"params": {
"project_id": "<GOOGLE_ASR_PROJECT_ID>",
"location": "global",
"adc_credentials_string": "<GOOGLE_APPLICATION_CREDENTIALS_STRING>",
"language": "en-US",
"model": "long"
}
}Caution
The parameters listed on this page are validated for use with Conversational AI Engine. Required parameters must be provided as documented. Any additional parameters are passed through directly to the underlying vendor without validation. For a full list of supported options, refer to the Google official documentation.
Key parameters
project_idstringThe Google Cloud project ID where the Speech-to-Text API is enabled. Get your project ID from the Google Cloud Console.
locationstringThe Google Cloud region where the speech service is hosted, for example, global, us-central1, or europe-west1.
adc_credentials_stringstringThe Google Cloud service account credentials JSON string used for authentication. Get your credentials from the Google Cloud Console.
languagestringThe language code for speech recognition, for example, en-US, es-ES, or fr-FR. See supported languages for available language codes.
modelstringThe recognition model to use.