## 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

| Model | Model Name | Scenario | Description |
| --- | --- | --- | --- |
| Speech Enhancement · Voice Isolation (General) | `VI_G_SE` | Noisy environment, human listener | SE · Voice Isolation (General) |
| Speech Enhancement Standard | `SE2.1` | Telephony audio restoration, low CPU | Restores and enhances voice quality, outputs 8kHz |
| Speech Enhancement with Full-Fidelity | `SE2.2` | Full-fidelity audio restoration | Bandwidth extension to ultra-fidelity 24kHz |
| Accent Translation | `AT5.2` | Accent Normalization | Add Accent Translation to your application to modifies global accents in real-time, allowing your teams to be instantly understood. |
| Language Translation | [LT](https://developer.sanas.ai/Docs/Language-Translation/Overview) | Voice-preserving Language translation | Add real-time speech-to-speech language translation to your application that preserves your speakers’ voices, tone, and intent. |

## Human ↔ Machine

| Model | Model Name | Scenario | Description |
| --- | --- | --- | --- |
| Agentic SE · Voice Isolation (General) | `AGENTIC_VI_G_SE` | Single speaker → ASR (16kHz) | Removes environmental noise and distant human voices. Single-speaker isolation for voice agents, IVR, phone bots |
| Agentic SE · Voice Isolation (Telephony) | `AGENTIC_VI_GT_SE` | Single speaker → ASR (8kHz telephony) | Telephony-optimized variant of Voice Isolation for 8kHz narrowband audio |
| Agentic SE · Standard | `AGENTIC_ST_SE` | Multiple speakers → ASR | Agentic SE · Standard Removes environmental noise, preserves distant human speech. Multi-speaker environments where background conversations carry context |

More models and model updates are coming soon.

## Still Not Sure?

Explore audio samples, full specifications, use cases, and code examples:

[**Speech Enhancement · Voice Isolation (General)**  
**`VI_G_SE`** 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 Speech Enhancement · 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)  
[LT](https://developer.sanas.ai/Docs/Models/Human-Human/Language-Translation/Language-Translation) Real-time language translation that preserves your speakers’ voices, tone, and intent.