## What is Sanas SDK?

The Sanas SDK processes speech audio in real time. You feed it audio frames and it returns processed audio frames — for example noise-cancelled, speech-enhanced, or accent-converted speech, or speech translated into another language. With **audio processing** (things like noise cancellation, speech enhancement, and accent conversion), you pick the specific model you want and the system cleans up or transforms the audio almost instantly.

**Language Translation** works a little differently. Instead of choosing a model, you just tell it the language someone is speaking and the language you want them heard in. Behind the scenes it does three jobs — transcribes the speech, translates it, and re-speaks it in the target language — and hands you back both the translated audio and a text transcript. Because it’s doing all three steps, it takes a few seconds longer than the audio-processing features, so it’s best suited to conversations where a slight delay is fine.

> **The good news: setting it up is the same either way. The connection, activation, and start-up steps are identical — Language Translation just needs the language settings instead of a model choice.**

The Python package ships as a **self-contained wheel**: everything the SDK needs is bundled inside it, so there is no separate native library to install or manage. You just create a virtual environment and `pip install` the wheel. You work with **interleaved float32 PCM** audio: push frames in with `process_frame` and read processed frames back. The SDK does not open microphones or speakers for you — you bring your own audio (from a file, a socket, a media stream, etc.). Enterprise-ready with [security](https://developer.sanas.ai/Docs/Enterprise/Security), [compliance](https://developer.sanas.ai/Docs/Enterprise/Compliance-and-Data-Residency), and [support](https://developer.sanas.ai/Docs/Enterprise/Support). Sanas also offers a standalone [Language Translation API](https://developer.sanas.ai/Docs/Language-Translation/Overview) for real-time speech-to-speech in the browser — if that’s your use case, start there instead of the SDK.

## What can you do with the Sanas SDK ?

- **Audio processing** — run a model (speech enhancement, accent conversion,…) over your audio, selected by a model key.
- **Language Translation (LT)** — translate speech from one language to another and receive both translated audio and transcript segments.
- **Pipeline lifecycle** — an `audio_pipeline_state_notify` callback reports the processing pipeline state (`PipelineState`); wait for `RUNNING` before feeding frames.

**Audio processing vs. Language Translation.** The SDK supports two modes that differ in how you select them and what they return. **Audio processing** (speech enhancement, noise cancellation, accent conversion) is chosen by setting a **model key** on `AudioAttributes.model_name` — for example `SE2.2` or `AT5.2` — and returns processed audio frames with minimal latency. **Language Translation (LT)** is selected instead by supplying a `LanguageTranslationConfig` (`lt_config`) and leaving `model_name` empty; you specify a source and target language rather than a model, and the pipeline returns both translated audio _and_ transcript segments via a callback. Because LT runs speech-to-text, translation, and text-to-speech end to end, it carries higher latency than the audio-processing models, so plan for a longer buffer/drain window. Everything else stays the same: you use the identical `create_sdk` → `activate_api_key` → `create_audio_processor` flow and wait for `PipelineState.RUNNING` before feeding frames.

This describes Language Translation **inside the Python SDK** (`lt_config`). For real-time speech-to-speech in the browser, Sanas also offers a standalone [Language Translation API](https://developer.sanas.ai/Docs/Language-Translation/Overview) — WebRTC / WebSocket / JavaScript client with an `init`/`configure` protocol. Use that instead of the SDK if you’re building a web app.

Key types: `InitParams`, `create_sdk`, `Sdk`, `AudioAttributes`, `ProcessorAttributes`, `AudioProcessor`, `AudioFrame`, `LanguageTranslationConfig`, `CloudInferencingParams`, `PipelineState`, `SdkResult`.

### How Audio processing works.

The Sanas SDK Connector sits between your application and Sanas Models, managing the connection to the inference engine. It sends input, receives processed output, and streams data in real-time using SIP (Session Initiation Protocol) and RTP (Real-Time Transport Protocol). The Sanas SDK can be deployed via [Sanas Cloud](https://developer.sanas.ai/Docs/Deployment/Sanas-Cloud) (recommended) or [self-hosted](https://developer.sanas.ai/Docs/Deployment/Self-Hosted) _(coming soon)_ on your own infrastructure.

Input

SDK Connector

Sanas Models

Output

## Core Capabilities

[**Speech Enhancement** \  
Isolate intended speech by removing background noise and voices — no quality degradation.](https://developer.sanas.ai/Docs/Models/Human-Human/NC-Voice-Isolation)

[**Speech Enhancement for Agentic Noise Cancellation** \  
Clean audio before ASR/STT. Isolate primary speakers and reduce Relative Word Error Rate (RWERR).](https://developer.sanas.ai/Docs/Models/Human-Machine/Agentic-NC-Voice-Isolation)

[**Speech Enhancement with full-fidelity** \  
Reconstruct and restore speech quality degraded by compression and network conditions.](https://developer.sanas.ai/Docs/Models/Human-Human/SE-Standard)

## Live Language Translation

Real-time cross-language voice communication.

## Accent Translation

Convert accents while preserving voice identity.

Sanas currently offers Speech Enhancement (audio clarification), Accent Translation, and Language Translation. Speech Intelligence coming soon.

## Available Models

[**Voice Isolation (General)** \  
**`VI_G_SE3.0`** Isolates intended speech by removing background noise and voices. Optimized for human listeners.](https://developer.sanas.ai/Docs/Models/Human-Human/NC-Voice-Isolation)

[**Speech Enhancement · Standard** \  
**`SE2.1`** Restores and enhances voice quality for telephony audio. Low CPU footprint.](https://developer.sanas.ai/Docs/Models/Human-Human/SE-Standard)

[**Speech Enhancement · Full-Fidelity** \  
**`SE2.2`** Full-fidelity speech enhancement with bandwidth extension to ultra-fidelity 24kHz.](https://developer.sanas.ai/Docs/Models/Human-Human/SE-Ultra)

[**Agentic Speech Enhancement· Voice Isolation (General)** \  
**`AGENTIC_VI_G_SE`** Removes background noise and distant voices for complete voice isolation of the primary speaker’s audio stream.](https://developer.sanas.ai/Docs/Models/Human-Machine/Agentic-NC-Voice-Isolation)

[**Agentic Noise Clarification · Voice Isolation (Telephony)** \  
**`AGENTIC_VI_GT_SE`** Telephony-optimized variant of Voice Isolation for 8kHz narrowband audio.](https://developer.sanas.ai/Docs/Models/Human-Machine/Agentic-NC-Voice-Isolation-Telephony)

[**Agentic Speech Enhancement · Standard** \  
**`AGENTIC_ST_SE`** Removes background noise while preserving all human speech for multi-speaker environments.](https://developer.sanas.ai/Docs/Models/Human-Machine/Agentic-NC-Standard)

[**Accent Translation** \  
**`AT5.2`** Accent Translation modifies global accents in real-time, allowing your teams to be instantly understood while preserving what makes every voice unique.](https://developer.sanas.ai/Docs/Models/Human-Machine/Agentic-NC-Standard)

[**Language Translation**](https://developer.sanas.ai/Docs/Models/Human-Human/Language-Translation/Language-Translation) Real-time language translation that preserves your speakers’ voices, tone, and intent.

See the [full model comparison →](https://developer.sanas.ai/Docs/Models/Overview)

## What You Can Build

## Voice Agents

Enhance voice agent pipelines with real-time speech and audio processing for clearer, more accurate interactions.

## Contact Centers

Power contact center audio at scale with concurrent stream processing and enterprise-grade reliability.

## Conferencing & Gaming

Deliver high-quality voice experiences across communication and interactive platforms.

## STT Pipelines

Improve speech-to-text accuracy by processing audio before it reaches your transcription engine.

## Key Features

## Real-Time Streaming

**Low-latency processing** Live audio processing with SIP/RTP

## High Concurrency

**Scalable solution** Process multiple audio streams simultaneously

## Session Management

**SIP protocol** Reliable connection establishment and management

## Seamless Communication

Enable clearer human-machine interactions across any environment

## Easy Integration

**Simple API** Initialize, create a processor, stream audio

## Secure

**Enterprise security** Encrypted transmission, secure authentication

## Ready to Build?

Request your API keys and integration credentials, then use the Quick Start to start streaming clean audio in minutes.

[**Quick Start**](https://developer.sanas.ai/Docs/Getting-Started/Quick-Start)  
Get up and running with Sanas SDK in under 5 minutes.

## Resources

[**Pricing**](https://developer.sanas.ai/Docs/Resources/Pricing)
Usage-based pricing.

[**Enterprise** \  
Data residency, compliance, security, and support.](https://developer.sanas.ai/Docs/Enterprise/Compliance-and-Data-Residency)

[**API Reference** \  
Complete API documentation for the Sanas SDK.](https://developer.sanas.ai/API-Reference/Overview)

[**Change Log**](https://developer.sanas.ai/Docs/Resources/Changelog)
Latest updates, releases, and fixes.