Updated
Use Google for text-to-speech (TTS) in a Conversational AI Platform agent.
Preview documentation
Google provides fast, reliable text-to-speech (TTS) with customizable voices.
Sample configuration
The following example shows how to configure Google TTS as the agent's TTS when you create or update an agent. For a complete example, see Create an agent and start a session.
Google TTS supports BYOK only. It isn't available in managed mode. Store your Google Cloud service account credentials JSON string in a secret set, and refer to it from the agent. For details, see Use your own provider keys.
from agora_agent import Agent, GoogleTTS, secret_ref
# client is your configured Agora client
agent = (
Agent(client=client)
.with_stt(...) # configure your ASR vendor
.with_llm(...) # configure your LLM vendor
.with_tts(
GoogleTTS(
key=secret_ref("support_prod", "google"),
voice_name="en-US-Chirp3-HD-Charon",
sample_rate_hertz=24000,
)
)
)import { Agent, GoogleTTS, secretRef } from 'agora-agents';
// client is your configured Agora client
const agent = new Agent({ client })
.withStt(/* configure your ASR vendor */)
.withLlm(/* configure your LLM vendor */)
.withTts(
new GoogleTTS({
key: secretRef('support_prod', 'google'),
voiceName: 'en-US-Chirp3-HD-Charon',
sampleRate: 24000,
}),
);// client is your configured Agora client
sampleRate := vendors.SampleRate24kHz
agent := agentkit.NewAgent(client).
WithStt( /* configure your ASR vendor */ ).
WithLlm( /* configure your LLM vendor */ ).
WithTts(vendors.NewGoogleTTS(vendors.GoogleTTSOptions{
Key: agentkit.SecretRef("support_prod", "google"),
VoiceName: "en-US-Chirp3-HD-Charon",
SampleRate: &sampleRate,
}))Set credential.mode to byok and credential.fields.credentials to a reference to your Google Cloud service account credentials JSON string. In the following example, the key is stored as google in the support_prod set:
"tts": {
"credential": {
"mode": "byok",
"fields": {
"credentials": "$secrets.support_prod.google"
}
},
"vendor": "google",
"params": {
"VoiceSelectionParams": {
"name": "en-US-Chirp3-HD-Charon"
},
"AudioConfig": {
"speaking_rate": 1.0,
"sample_rate_hertz": 24000
}
}
}Key parameters
The tts block takes the following fields. In the SDKs, GoogleTTS sets them from its options.
vendorstringSet to google.
credentialobjectSet mode to byok and fields.credentials to a $secrets.<set>.<key> reference to your Google Cloud service account credentials JSON string. Get your credentials from the Google Cloud Console.
paramsobjectVoiceSelectionParamsobjectnamestringThe name of the voice to use, for example, en-US-Chirp3-HD-Charon or en-US-Neural2-A. See supported voices for available voice names.
AudioConfigobjectspeaking_ratenumberThe speed of speech. Valid range is 0.25 to 2.0, where 1.0 is the normal speed. Values less than 1.0 slow down the speech, while values greater than 1.0 speed it up.
sample_rate_hertzintegerThe sample rate in Hertz for the audio output, for example, 24000 or 16000. The default value depends on the selected voice.
Caution
The parameters listed on this page are validated for use with the Conversational AI Platform. Required parameters must be provided as documented. Any additional parameters in params are passed through directly to Google without validation. For a full list of supported options, refer to the Google documentation.
This integration is fully supported for use with the Conversational AI Platform. 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.