• Supported service: tts
  • Key: google_tts
  • Integrated: No. See BYO Keys for more info.
    • Google requires a Google Cloud Platform account with the Cloud Text-to-Speech API enabled.
    • You’ll need to create a service account for your project and use the service account credentials object to authenticate with the Google Cloud API.
    • Follow the Google Cloud docs to create a service account and access your credentials.
    • Your service account object sould look something like this:
    {
 "type":"service_account",
 "project_id":"PROJECT_ID",
 "private_key_id":"PRIVATE_KEY_ID",
 "private_key":"-----BEGIN PRIVATE KEY-----\\PRIVATE_KEY-----END PRIVATE KEY-----\n",
 "client_email":"CLIENT_EMAIL",
 "client_id":"CLIENT_ID",
 "auth_uri":"https://accounts.google.com/o/oauth2/auth",
 "token_uri":"https://oauth2.googleapis.com/token",
 "auth_provider_x509_cert_url":"https://www.googleapis.com/oauth2/v1/certs",
 "client_x509_cert_url":"CERT_URL",
 "universe_domain":"googleapis.com"
}

​
Service options

sample_rate
integer
default: "24000"

The audio output sample rate in Hz for the TTS audio.

The sample rate must be one of these values: 8000, 16000, 22050, 24000, 32000, 44100, 48000.

{
  "service_options": {
    "google_tts": {
      "sample_rate": 24000
    }
  }
}

​
Configuration options

voice
string
required

The voice you want your TTS service to use. Select any voice from the available Google TTS voices.

{
  "name": "voice",
  "value": "en-US-Neural2-J"
}
language
string
default: "en-US"

The language you the TTS service to use. Select any language from the available Google TTS languages.

Note: the language option must be compatible with the voice option.

{
  "name": "language",
  "value": "en-US"
},
{
  "name": "voice",
  "value": "en-US-Neural2-J"
}
pitch
string

The pitch of the voice. Learn more about using pitch with Google here.

{
  "name": "pitch",
  "value": "medium"
}
rate
string

The rate of the voice. Learn more about using rate with Google here.

{
  "name": "rate",
  "value": "slow"
}
volume
string

The volume of the voice. Learn more about using volume with Google here.

{
  "name": "volume",
  "value": "loud"
}
emphasis
string

Adjust the emphasis for the voice. Learn more.

Values accepted are: strong, moderate, reduced, and none.

{
  "name": "emphasis",
  "value": "moderate"
}
text_filter
object

Control whether the TTS service filters out markdown, code blocks, or tables from its output.

Basic markdown filtering is enabled by default. Enable code and table filtering as needed. Filtering code and tables can help the TTS avoid mistakes.

{
  "name": "text_filter",
  "value": {
    "enable_text_filter": true,
    "filter_code": true,
    "filter_tables": true
  }
}
ElevenLabsOpenAI