MiniMax

MiniMax provides text-to-speech (TTS) with multiple voice styles and low-latency streaming output.

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

_12

"tts": {

_12

"vendor": "minimax",

_12

"params": {

_12

"api_key": "<minimax_key>",

_12

"group_id": "<minimax_group_id>",

_12

"model": "speech-02-turbo",

_12

"voice_setting": {

_12

"voice_id": "English_captivating_female1"

_12

},

_12

"url": "wss://api-uw.minimax.io/ws/v1/t2a_v2"

_12

}

_12

}

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 MiniMax documentation.

ttsrequired

• api_key stringrequired

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

• group_id stringrequired

  The MiniMax group identifier. This is required for your account’s configuration.

• model stringrequired

  The TTS model to use. For example, speech-02-turbo.

• voice_setting.voice_id stringrequired

  The voice style identifier to use. For example, English_captivating_female1.

• url stringrequired

  The WebSocket endpoint for streaming TTS output. For example, wss://api-uw.minimax.io/ws/v1/t2a_v2.