Get up and running with Sanas SDK in 5 minutes
New to Sanas? This guide will take you from zero to processing your first audio stream in under 5 minutes.
Prerequisites Before you begin, ensure you have:
Ubuntu 22.04 x86-64 (other Linux distros coming soon)Python 3.10 or higher SDK credentials – Request access if you don’t have them yet
Step 1: Install the SDK
Download your SDK connector file (e.g., sanas_remote_sdk_<platform-arch>_<version>.tar.gz) included along with the welcome email from Sanas.
Extract and install:
tar -zxvf sanas_remote_sdk_ < platform-arc h > _ < versio n > .tar.gz cd sanas_remote_sdk_ < platform-arc h > _ < versio n > ./install.sh
Verify installation source sanas_remote_sdk/bin/activate python3 -c "import sanas_remote_sdk; print('SDK installed successfully!')"
Step 2: Choose Your AI Model Which problem are you solving?
🤖 AI Voice Agents
📞 Human Calls
Problem: Your voice agent has poor ASR accuracy in noisy environmentsSolution: AI Voice Agent model (improves WER by 5-30%)Model name: AGENTIC_NCSample rate: ≤ 16 kHzLearn more about this model → Problem: Background noise on calls (office, street, home)Solution: Noise Cancellation
Model name: VI_G_NC3.0 (General Purpose)Sample rate: ≤ 24 kHz Compare NC models → Step 3: Run Your First Example Copy and paste this complete working example:
Example: AI Voice Agent
Example: Noise Cancellation (General)
import sanas_remote_sdk # Initialize SDK sdk = sanas_remote_sdk.CreateRemoteSDK() init_params = sanas_remote_sdk.InitParams() init_params.remoteEndpoint = "your_endpoint_url" # From credentials email init_params.accountId = "your_account_id" init_params.accountSecret = "your_account_secret" init_params.secureMedia = True result = sdk.Initialize(init_params) print ( f "SDK initialized: { result } " ) # State callback def state_callback ( state , reason ): if state == sanas_remote_sdk.ProcessorState. READY : print ( "Processor ready!" ) # Create an audio processor audio_params = sanas_remote_sdk.AudioParams() audio_params.modelName = "AGENTIC_NC" audio_params.sampleRate = 16000 #Define source audio sampling rate processor, create_result = sdk.CreateAudioProcessor(audio_params, state_callback) if create_result == sanas_remote_sdk.CreateProcessorResult. SUCCESS : # Process audio chunks (example with dummy data) input_audio = [ 0.1 ] * 320 # 20ms at 16kHz output_audio = processor.ProcessSamples(input_audio) print ( f "Processed { len (output_audio) } samples" ) # Now send output_audio to your ASR system # Cleanup sdk.DestroyAudioProcessor(processor) sdk.Shutdown()
Step 4: Next Steps Support Reach out to our support for any assistance:
