Skip to main content

Murf (Beta)

Murf provides enterprise-grade AI voice generation with text-to-speech (TTS) models.

Sample configuration

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


_15
"tts": {
_15
"vendor": "murf",
_15
"params": {
_15
"api_key": "<murf_api_key>",
_15
"base_url": "wss://global.api.murf.ai/v1/speech/stream-input",
_15
"voiceId": "Matthew",
_15
"multiNativeLocale": "en-US",
_15
"style": "Conversation",
_15
"rate": 0,
_15
"pitch": 0,
_15
"variation": 1,
_15
"model": "FALCON",
_15
"sample_rate": 24000
_15
}
_15
}

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 Murf documentation.

ttsrequired
  • api_key stringrequired

    The Murf API key used to authenticate requests. You must provide a valid key for the service to function.

  • base_url stringnullable

    The WebSocket endpoint for streaming TTS output. For example, wss://global.api.murf.ai/v1/speech/stream-input.

  • voiceId stringnullable

    The voice identifier to use. For example, Matthew.

  • multiNativeLocale stringnullable

    The locale for the selected voice. For example, en-US.

  • style stringnullable

    The speaking style to apply. For example, Conversation.

  • rate numbernullable

    The speech rate adjustment. A value of 0 applies the default rate.

  • pitch numbernullable

    The pitch adjustment. A value of 0 applies the default pitch.

  • variation numbernullable

    The voice variation setting. For example, 1.

  • model stringnullable

    The TTS model to use. For example, FALCON.

  • sample_rate numbernullable

    The audio sample rate in Hz. For example, 24000.