Skip to main content

OpenAI (Beta)

OpenAI provides natural-sounding text-to-speech with customizable voice instructions and multiple voice options.

Sample configuration

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


_10
"tts": {
_10
"vendor": "openai",
_10
"params": {
_10
"api_key": "<llm_api_key_openai>",
_10
"model": "gpt-4o-mini-tts",
_10
"voice": "coral",
_10
"instructions": "Please use standard American English, natural tone, moderate pace, and steady intonation",
_10
"speed": 1
_10
}
_10
}

Key parameters

paramsrequired
  • api_key stringrequired

    The API key used for authentication. Get your API key from the OpenAI Console.

  • model stringrequired

    Identifier of the model to be used.

  • voice stringrequired

    The voice identifier for speech synthesis.

  • instructions stringnullable

    Custom instructions for voice style, accent, pace, and tone. Helps fine-tune the speech characteristics.

  • speed numbernullable

    Default: 1.0

    Speaking rate multiplier. Values between 0.25 and 4.0, where 1.0 is normal speed.

info

OpenAI TTS models do not support changing the sample rate. The audio output is fixed at 24,000 Hz.

For advanced configuration options, available voices, and detailed parameter descriptions, see the OpenAI TTS documentation.