Sanas Developer Hub
Docs
- Glossary: Definitions of Sanas Speech AI SDK terms and concepts
- API Lifecycle: The six-step sequence every SDK integration follows
- Audio Format & Sending Audio: Input requirements, real-time pacing, and PCM conversion for ProcessSamples
- Installation & Linking: Install, compile, and link the Sanas Speech AI SDK, then authenticate with your API key
- Language Translation: Create a translation processor, choose languages, auto-detect, and switch languages live
- Processor State Handling: Wait for kReady before sending audio — via callback or polling
- Quick Start — Language Translation: A complete, end-to-end C++ Language Translation program
- Threading & Lifetime Rules: Thread-safety, callback constraints, and object lifetime for the SDK
- Transcripts: Handle source and target transcript events delivered as JSON via callback
- Troubleshooting & Support: Common symptoms and fixes, plus support resources
- C++ SDK Overview: Real-time access to the Sanas cloud speech platform from a C++17 application
- Configuration Reference: InitParams, AudioParams, LanguageConfig, and JitterParams
- Core Classes: IRemoteSDK and IAudioProcessor — the two interfaces your application uses
- Result Codes: Return-value enums for Initialize, CreateAudioProcessor, UpdateLanguageConfig, and cleanup
- State Enum & Callbacks: ProcessorState, ProcessorStateChange, and the state/transcript callback signatures
- Overview: Full API documentation for the Sanas SDK
- AudioProcessor
- RemoteSDK
- AudioParams
- InitParams
- CreateProcessorResult
- DestroyProcessorResult
- InitSDKResult
- ShutdownSDKResult
- State Callbacks
- ProcessorState
- Sanas Cloud: Cloud-hosted deployment for the Sanas SDK
- Self-Hosted (Coming Soon): Self-hosted deployment for the Sanas SDK
- Compliance & Data Residency
- Security
- Support
- Set up account: Create a developer account.
- Overview of Sanas: Get started building with real-time speech AI using the Sanas SDK
- Quick Start: Get up and running with the Sanas SDK in under 5 minutes.
- Language Translation: Add real-time speech-to-speech translation to your application with WebRTC, WebSocket, and REST APIs
- REST API: HTTP endpoints for account management, device registration, language listing, and Twilio video integration
- Stream Message Layer: The shared application protocol for the WebSocket Stream API and the WebRTC API
- WebRTC API: Browser-native transport for the Stream API using WebRTC data channels and media tracks
- WebSocket API: Real-time speech-to-speech translation over a single persistent WebSocket connection
- Choose Your Model: Find the right Sanas model for your use case
- SE - Voice Isolation: Real-time voice isolation for any acoustic environment.
- SE - Standard: Real-time speech enhancement optimized for 8kHz telephony audio
- SE with full-fidelity: Real-time speech enhancement with bandwidth extension to 24kHz ultra-fidelity audio
- Models Overview
- Changelog: All updates, fixes, and breaking changes to the Sanas SDK
- Pricing
- Sanas Developer Platform — FAQ
- Processing Multiple Streams: Run many concurrent audio processors on a single SDK instance, and benchmark throughput, concurrency, and memory.
- Processing a Single Stream: Run a WAV file through the Sanas SDK end to end — activate, wait for RUNNING, feed 20 ms frames, and drain the tail.
- Language Translation: Translate speech from one language to another and receive both translated audio and transcript segments.
- Accent Translation: Real-time accent modulation that preserves voice identity and emotion.
- Agentic SE Voice Isolation (Telephony): ASR-optimized speech enhancement for telephony audio pipelines
- Agentic SE Standard: ASR-optimized speech enhancement with speech preservation for multi-speaker environments
- Agentic SE Voice Isolation: ASR-optimized speech enhancement for voice AI pipelines
OpenAPI Specs