Sarvam (Beta)

Sarvam provides fast, reliable text-to-speech (TTS) with support for Indian languages and customizable voices.

The following example shows a starting tts parameter configuration you can use when you Start a conversational AI agent.

_8

"tts": {

_8

"vendor": "sarvam",

_8

"params": {

_8

"api_subscription_key": "<SARVAM_API_KEY>",

_8

"speaker": "anushka",

_8

"target_language_code": "en-IN"

_8

}

_8

}

caution

The parameters listed on this page are validated for use with Conversational AI Engine. To avoid unpredictable behavior, Agora strongly recommends using only the supported parameters. For a complete reference, consult the Sarvam documentation.

paramsrequired

• api_subscription_key stringrequired

  The API key used for authentication. Get your API key from the Sarvam dashboard.

• speaker stringrequired

  The voice ID to use for speech generation.

  • Female voices: anushka, manisha, vidya, arya.
  • Male voices: abhilash, karun, hitesh.
• target_language_code stringrequired

  The language code for speech synthesis. Supported values:

  • en-IN English (India)
  • hi-IN: Hindi
  • bn-IN: Bengali
  • ta-IN: Tamil
  • te-IN: Telugu
  • kn-IN: Kannada
  • ml-IN: Malayalam
  • mr-IN: Marathi
  • gu-IN: Gujarati
  • pa-IN: Punjabi
  • or-IN: Odia
• pitch numbernullable

  Range: [-0.75, 0.75]

  The pitch adjustment for the voice. Positive values make the voice sharper; negative values make it deeper.

• pace numbernullable

  Range: [0.3, 3.0]

  The speed of speech. 1.0 is the normal speed. Values less than 1.0 slow down the speech; values greater than 1.0 speed it up.

• loudness numbernullable

  Range: [0.1, 3.0]

  The volume level of the speech. Higher values increase the loudness.

• sample_rate numbernullable

  Possible values: 8000, 16000, 22050, 24000

  The audio sample rate in Hz.