Gradium
Updated
Integrate Gradium TTS with the Conversational AI Engine.
Gradium provides enterprise-grade AI voice generation with text-to-speech (TTS) models.
Info
This integration is fully supported for use with Conversational AI Engine. While it has completed functional validation, it is newer to the platform, and additional provider-specific edge cases may be identified as usage scales across a broader range of applications and workloads.
Sample configuration
The following examples show how to configure Gradium TTS when starting a conversational AI agent.
from agora_agent import Agent
from agora_agent.agentkit.vendors import GradiumTTS
# client is your configured Agora client
agent = (
Agent(client)
.with_stt(...) # configure your STT vendor
.with_llm(...) # configure your LLM vendor
.with_tts(GradiumTTS(
api_key='<GRADIUM_API_KEY>',
url='wss://api.gradium.ai/api/speech/tts',
model_name='default',
voice_id='<GRADIUM_VOICE_ID>',
sample_rate=16000,
))
)import { Agent, GradiumTTS } 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 GradiumTTS({
apiKey: '<GRADIUM_API_KEY>',
url: 'wss://api.gradium.ai/api/speech/tts',
modelName: 'default',
voiceId: '<GRADIUM_VOICE_ID>',
sampleRate: 16000,
}));import "github.com/AgoraIO/agora-agents-go/v2/agentkit/vendors"
// client is your configured Agora client
sampleRate := vendors.SampleRate16kHz
agent := agentkit.NewAgent(client).WithStt(/* configure your STT vendor */).
WithLlm(/* configure your LLM vendor */).
WithTts(
vendors.NewGradiumTTS(vendors.GradiumTTSOptions{
APIKey: "<GRADIUM_API_KEY>",
URL: "wss://api.gradium.ai/api/speech/tts",
ModelName: "default",
VoiceID: "<GRADIUM_VOICE_ID>",
SampleRate: &sampleRate,
}),
)Use the following tts configuration in your request:
"tts": {
"vendor": "gradium",
"params": {
"api_key": "<GRADIUM_API_KEY>",
"url": "wss://api.gradium.ai/api/speech/tts",
"model_name": "default",
"voice_id": "<GRADIUM_VOICE_ID>",
"sample_rate": 16000
}
}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 Gradium documentation.
Key parameters
api_keystringThe Gradium API key used to authenticate requests. You must provide a valid key for the service to function.
urlstringThe WebSocket endpoint for streaming TTS output. For example, wss://api.gradium.ai/api/speech/tts.
model_namestringThe TTS model to use. For example, default.
voice_idstringThe voice identifier to use.
sample_ratenumberThe audio sample rate in Hz. For example, 16000.