MiniMax
Updated
Integrate MiniMax TTS with the Conversational AI Engine.
MiniMax provides text-to-speech (TTS) with multiple voice styles and low-latency streaming output.
Sample configuration
The following examples show how to configure MiniMax TTS when starting a conversational AI agent.
from agora_agent import Agent
from agora_agent.agentkit.vendors import MiniMaxTTS
# client is your configured Agora client
agent = (
Agent(client)
.with_stt(...) # configure your STT vendor
.with_llm(...) # configure your LLM vendor
.with_tts(MiniMaxTTS(
key='your-minimax-key', # omit key, group_id, voice_id, and url to use Agora-managed mode
group_id='your-minimax-group-id',
model='speech-2.8-turbo',
voice_id='English_captivating_female1',
url='wss://api-uw.minimax.io/ws/v1/t2a_v2',
))
)import { Agent, MiniMaxTTS } from 'agora-agents';
// client is your configured Agora client
const agent = new Agent({ client })
.withStt(/* configure your STT vendor */)
.withLlm(/* configure your LLM vendor */)
.withTts(new MiniMaxTTS({
key: 'your-minimax-key', // omit key, groupId, voiceId, and url to use Agora-managed mode
groupId: 'your-minimax-group-id',
model: 'speech-2.8-turbo',
voiceId: 'English_captivating_female1',
url: 'wss://api-uw.minimax.io/ws/v1/t2a_v2',
}));import "github.com/AgoraIO/agora-agents-go/v2/agentkit/vendors"
// client is your configured Agora client
agent := agentkit.NewAgent(client).WithStt(/* configure your STT vendor */).
WithLlm(/* configure your LLM vendor */).
WithTts(
vendors.NewMiniMaxTTS(vendors.MiniMaxTTSOptions{
Key: "your-minimax-key", // omit Key, GroupID, VoiceID, and URL to use Agora-managed mode
GroupID: "your-minimax-group-id",
Model: "speech-2.8-turbo",
VoiceID: "English_captivating_female1",
URL: "wss://api-uw.minimax.io/ws/v1/t2a_v2",
}),
)-
Managed mode
To use MiniMax TTS with Agora-managed credentials, set
credential_modeto"managed"in thettsblock. When using managed mode,params.keyandparams.group_idare not required. You can still use thettsfield to configure additional settings such asvoice_setting. For more information, see Use managed mode."tts": { "credential_mode": "managed", "vendor": "minimax", "params": { "url": "wss://api.minimax.io/ws/v1/t2a_v2", "model": "speech-2.8-turbo", "voice_setting": { "voice_id": "English_captivating_female1", "speed": 1.0 }, "audio_setting": { "sample_rate": 44100 } } } -
BYOK
"tts": { "vendor": "minimax", "params": { "key": "<minimax_key>", "group_id": "<minimax_group_id>", "model": "speech-2.8-turbo", "url": "wss://api-uw.minimax.io/ws/v1/t2a_v2", "voice_setting": { "voice_id": "English_captivating_female1", "speed": 1.0 }, "audio_setting": { "sample_rate": 44100 } } }
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 MiniMax documentation.
Key parameters
The following parameters are required when using your own API key (BYOK). When using managed mode, key and group_id are not required. For more information, see Use managed mode.
keystringThe MiniMax API key used to authenticate requests. Required when using your own API key (BYOK).
group_idstringThe MiniMax group identifier. Required when using your own API key (BYOK).
urlstringThe WebSocket endpoint for streaming TTS output. For example, wss://api-uw.minimax.io/ws/v1/t2a_v2.
modelstringThe TTS model to use. For example, speech-02-turbo.
voice_setting.voice_idstringThe voice style identifier to use. For example, English_captivating_female1.
audio_setting.sample_ratenumberThe audio sampling rate in Hz.