Not sure which model to use? Answer one question to find the right fit.Documentation Index
Fetch the complete documentation index at: https://developer.sanas.ai/llms.txt
Use this file to discover all available pages before exploring further.
Who is listening?
A person is listening
You need a Human ↔ Human model. Voice quality and naturalness matter.
A machine is listening
You need a Human ↔ Machine model. Relative Word Error Rate (RWERR) reduction and ASR accuracy matter.
Human ↔ Human
| Scenario | Model | Description |
|---|---|---|
| Noisy environment, human listener | NC · Voice Isolation (General)VI_G_NC3.0 | Removes background noise, preserves voice character |
| Telephony audio restoration, low CPU | SE StandardSE2.1 | Restores and enhances voice quality, outputs 8kHz |
| Full-fidelity audio restoration | SE UltraSE2.2 | Bandwidth extension to ultra-fidelity 24kHz |
Human ↔ Machine
| Scenario | Model | Description |
|---|---|---|
| Single speaker → ASR (16kHz) | Agentic NC · Voice Isolation (General)AGENTIC_VI_G_NC | Removes environmental noise and distant human voices. Single-speaker isolation for voice agents, IVR, phone bots |
| Single speaker → ASR (8kHz telephony) | Agentic NC · Voice Isolation (Telephony)AGENTIC_VI_GT_NC | Telephony-optimized variant of Voice Isolation for 8kHz narrowband audio |
| Multiple speakers → ASR | Agentic NC · StandardAGENTIC_ST_NC | Removes environmental noise, preserves distant human speech. Multi-speaker environments where background conversations carry context |
Still Not Sure?
Explore audio samples, full specifications, use cases, and code examples:Noise Cancellation · Voice Isolation (General)
VI_G_NC3.0 Human ↔ HumanIsolates intended speech by removing background noise and voices. Optimized for human listeners.Speech Enhancement · Standard
SE2.1 Human ↔ HumanRestores and enhances voice quality for telephony audio. Low CPU footprint.Speech Enhancement · Ultra
SE2.2 Human ↔ HumanFull-fidelity speech enhancement with bandwidth extension to ultra-fidelity 24kHz.Agentic Noise Cancellation · Voice Isolation (General)
AGENTIC_VI_G_NC Human ↔ MachineRemoves background noise and distant voices for complete voice isolation of the primary speaker’s audio stream.Agentic Noise Cancellation · Voice Isolation (Telephony)
AGENTIC_VI_GT_NC Human ↔ MachineTelephony-optimized variant of Voice Isolation for 8kHz narrowband audio.Agentic Noise Cancellation · Standard
AGENTIC_ST_NC Human ↔ MachineRemoves background noise while preserving all human speech for multi-speaker environments.