Sarvam
Updated
Integrate Sarvam ASR with the Conversational AI Engine.
Sarvam ASR provides real-time speech-to-text with low latency and reliable performance for Indian languages.
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 example shows how to configure Sarvam ASR when starting a conversational AI agent.
from agora_agent import Agent, SarvamSTT
# client is your configured Agora client
agent = (
Agent(client)
.with_stt(SarvamSTT(
api_key='your-sarvam-key',
language='hi-IN',
))
.with_llm(...) # configure your LLM vendor
.with_tts(...) # configure your TTS vendor
)import { Agent, SarvamSTT } from 'agora-agents';
// client is your configured Agora client
const agent = new Agent({ client })
.withStt(new SarvamSTT({
apiKey: 'your-sarvam-key',
language: 'hi-IN',
}))
.withLlm(/* configure your LLM vendor */)
.withTts(/* configure your TTS vendor */);import "github.com/AgoraIO/agora-agents-go/v2/agentkit/vendors"
// client is your configured Agora client
agent := agentkit.NewAgent(client).WithStt(
vendors.NewSarvamSTT(vendors.SarvamSTTOptions{
APIKey: "your-sarvam-key",
Language: "hi-IN",
}),
).WithLlm(/* configure your LLM vendor */).
WithTts(/* configure your TTS vendor */)Use the following asr configuration in your request:
"asr": {
"vendor": "sarvam",
"language": "en-US",
"params": {
"api_key": "SARVAM_KEY",
"language": "hi-IN"
}
}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 Sarvam documentation.
Key parameters
api_keystringYour Sarvam API key. Get your API key from the Sarvam dashboard.
languagestringThe language code for transcription. Set to unknown for automatic language detection.