MiniMax
Updated
Use MiniMax for text-to-speech (TTS) in a Conversational AI Platform agent.
Preview documentation
MiniMax provides text-to-speech (TTS) with multiple voice styles and low-latency streaming output.
Sample configuration
The following example shows how to configure MiniMax as the agent's TTS when you create or update an agent. For a complete example, see Create an agent and start a session.
MiniMax supports managed mode and BYOK. In managed mode, Agora provides access to MiniMax, and you don't need a MiniMax account. For BYOK, store your MiniMax API key in a secret set, and refer to it from the agent. For details, see Use managed mode and Use your own provider keys.
from agora_agent import Agent, MiniMaxTTS, secret_ref
# client is your configured Agora client
agent = (
Agent(client=client)
.with_stt(...) # configure your ASR vendor
.with_llm(...) # configure your LLM vendor
.with_tts(
MiniMaxTTS(
key=secret_ref("support_prod", "minimax"), # omit to use managed mode
group_id="<your_minimax_group_id>", # omit to use managed mode
url="wss://api-uw.minimax.io/ws/v1/t2a_v2", # omit to use managed mode
model="speech-2.8-turbo",
voice_id="English_captivating_female1",
speed=1.0,
sample_rate=44100,
)
)
)import { Agent, MiniMaxTTS, secretRef } from 'agora-agents';
// client is your configured Agora client
const agent = new Agent({ client })
.withStt(/* configure your ASR vendor */)
.withLlm(/* configure your LLM vendor */)
.withTts(
new MiniMaxTTS({
key: secretRef('support_prod', 'minimax'), // omit to use managed mode
groupId: '<your_minimax_group_id>', // omit to use managed mode
url: 'wss://api-uw.minimax.io/ws/v1/t2a_v2', // omit to use managed mode
model: 'speech-2.8-turbo',
voiceId: 'English_captivating_female1',
speed: 1.0,
sampleRate: 44100,
}),
);// client is your configured Agora client
speed, sampleRate := 1.0, 44100
agent := agentkit.NewAgent(client).
WithStt( /* configure your ASR vendor */ ).
WithLlm( /* configure your LLM vendor */ ).
WithTts(vendors.NewMiniMaxTTS(vendors.MiniMaxTTSOptions{
Key: agentkit.SecretRef("support_prod", "minimax"), // omit to use managed mode
GroupID: "<your_minimax_group_id>", // omit to use managed mode
URL: "wss://api-uw.minimax.io/ws/v1/t2a_v2", // omit to use managed mode
Model: "speech-2.8-turbo",
VoiceID: "English_captivating_female1",
Speed: &speed,
SampleRate: &sampleRate,
}))-
Managed mode
Set
credential.modetomanagedin thettsblock. Agora provides access to MiniMax, and you don't need a MiniMax account."tts": { "credential": { "mode": "managed" }, "vendor": "minimax", "params": { "model": "speech-2.8-turbo", "voice_setting": { "voice_id": "English_captivating_female1", "speed": 1.0 }, "audio_setting": { "sample_rate": 44100 } } } -
BYOK
Set
credential.modetobyokandcredential.fields.keyto a reference to your MiniMax API key in a secret set. Your MiniMax group ID isn't secret. Pass it inparams. In the following example, the key is stored asminimaxin thesupport_prodset:"tts": { "credential": { "mode": "byok", "fields": { "key": "$secrets.support_prod.minimax" } }, "vendor": "minimax", "url": "wss://api-uw.minimax.io/ws/v1/t2a_v2", "params": { "group_id": "<your_minimax_group_id>", "model": "speech-2.8-turbo", "voice_setting": { "voice_id": "English_captivating_female1", "speed": 1.0 }, "audio_setting": { "sample_rate": 44100 } } }
Key parameters
The tts block takes the following fields. In the SDKs, the MiniMax TTS class sets them from its options.
vendorstringSet to minimax.
credentialobjectHow the agent authenticates with MiniMax. Set mode to managed, or to byok with fields.key set to a $secrets.<set>.<key> reference to your MiniMax API key.
urlstringA custom WebSocket endpoint for streaming TTS output, for example wss://api-uw.minimax.io/ws/v1/t2a_v2. Not needed in managed mode.
paramsobjectgroup_idstringThe MiniMax group identifier. Required for BYOK.
modelstringThe TTS model to use, for example speech-02-turbo. For managed mode, use speech-2.6-turbo or speech-2.8-turbo.
voice_setting.voice_idstringThe voice style identifier to use, for example English_captivating_female1.
voice_setting.speednumberThe speaking speed, for example 1.0.
audio_setting.sample_ratenumber- Possible values
80001600022050240003200044100
The audio sampling rate in Hz.
Caution
The parameters listed on this page are validated for use with the Conversational AI Platform. Required parameters must be provided as documented. Any additional parameters in params are passed through directly to MiniMax without validation. For a full list of supported options, refer to the MiniMax documentation.