# Voice Harbor
Source: https://docs.nijta.com/Biometric

Learn how to redact biometric voiceprints in audio file using Voice Harbor's API.

<CardGroup>
  <Card title="Access Token" icon="key" href="https://voiceharbor.ai">
    Automatically redact biometric identifiers from audio for privacy compliance.
  </Card>
</CardGroup>

## Voice Harbor V4.0 Release

<Update label="September 2025 Release" description="Voice Harbor V4.0">
  | Category               | V3.0                  | V4.0                            |
  | ---------------------- | --------------------- | ------------------------------- |
  | Expressiveness         | Neutral only          | Emotional expressiveness        |
  | Language Support       | Core set              | Extended European languages     |
  | Control Parameters     | Age, gender, language | +Expressiveness control         |
  | Audio Quality          | 16 kHz                | 22 kHz (Mini + Advanced)        |
  | Word Error Rate (WER)  | Baseline              | −58% (Mini), −62% (Advanced)    |
  | MOS (Naturalness)      | 3.72                  | 4.15 (≈ +12%)                   |
  | Processing Speed (RTF) | \~1.5×                | Mini: \<0.5×, Advanced: \~0.75× |

  With **V4**, Voice Harbor delivers clearer, faster, and more natural anonymized speech—without sacrificing privacy. Both **Mini** (optimized for speed) and **Advanced** (optimized for quality) modes are now more efficient than ever, and both output at **22 kHz**.

  #### Features

  * **Biometric Voiceprint Redaction:** Stronger anonymization to protect identity.
  * **Prosody & Emotion Preservation:** Natural intonation with emotional expressiveness.
  * **Enhanced Multilingual Support:** Broader coverage across European languages.
  * **Faster & Higher Quality:** 22 kHz output with up to **3×** faster processing.

  #### VPC2024 Evaluation Scores

  | Model                 | **EER ↓** | **UAR ↑** | **WER ↓** |
  | --------------------- | --------- | --------- | --------- |
  | B1                    | 10        | 42        | 2.9       |
  | B2                    | 13        | 55        | 10.0      |
  | B5                    | 36        | 38        | 4.4       |
  | B6                    | 25        | 36        | 9.1       |
  | SHIVA Orange          | 41        | 41        | 7.8       |
  | South Korea           | 44        | 28        | 5.0       |
  | FreeVC                | 35        | 44        | 4.5       |
  | NTU-NPU               | 42        | 40        | 4.5       |
  | Voice Harbor V3.0     | 44        | 40        | 3.8       |
  | **Voice Harbor V4.0** | **42**    | **38**    | **2.7**   |
</Update>

<Update label="Mai 2025 Release" description="Voice Harbor V3.0">
  ## Changelog

  #### Features

  * **Biometric voiceprints Redaction:** Remove unique vocal traits to protect your identity.
  * **Emotion Preservation:** Retain the natural emotional tone of your speech.
  * **High-quality Voices:** Generate clear, natural-sounding audio.
  * **Generative Content Anonymization:** Edit words and phrases for a tailored message.
</Update>

<Update label="2024-04-01" description="Voice Harbor V2.0">
  ## Changelog

  [Voice Harbor V2.0](https://app.nijta.com/) introduces a cutting-edge approach to secure speech data transformation, prioritizing privacy and compliance. This version features advanced biometric identity redaction, ensuring sensitive audio content is anonymized while maintaining clarity and usability. Fully approved by CNIL, V2.0 upholds the highest standards for data protection, making it an ideal solution for a wide range of applications requiring secure voice processing.

  #### Features

  * **Biometric voiceprints Redaction:** Remove unique vocal traits to protect your identity.
  * **Regulatory Compliance:** Ensure privacy standards with CNIL-guaranteed protection.
</Update>


# Voice Harbor Plugins
Source: https://docs.nijta.com/BuildwithVoiceHarbor/Plugins

Enjoy Voice Harbor inside Avid Pro Tools

## AAX Plugin Release

First public release of the Voice Harbor AAX plugin by Nijta, providing advanced voice anonymization for media workflows.
Voice Harbor delivers studio-grade anonymization while preserving vocal naturalness, enabling compliant use of sensitive audio under global privacy regulations.

### Features

* 🌍 Multilingual support: English, German, French, Italian, and Spanish
* ⚙️ Selective voice attribute control: modify or preserve gender, age group, and emotion after anonymization
* ⚡ Lightning-fast performance: \~0.25× real-time processing speed
* 🎧 Production-grade audio quality output for seamless integration in broadcast and post-production pipelines
* 🔒 Regulatory compliance: GDPR / EU AI Act / HIPAA / CCPA-ready anonymization

<CardGroup>
  <Card title="Access Voice Harbor AAX Plugin" icon="key" href="https://voiceharbor.ai">
    Automatically redact biometric identifiers from audio for privacy compliance.
  </Card>
</CardGroup>

***

## Installation Guide

### Step 1 – Download the Plugin

Go to [Voice Harbor Plugins](https://voiceharbor.ai) and download the **Voice Harbor AAX plugin**.

### Step 2 – Run the Installer

Double-click the package `VoiceHarbor-ProTools-macOS.pkg` to start installation.

<img alt="IMG2" />

### Step 3 – Authorize Installation

Enter your macOS password to complete the installation process and close the installer window.

<img alt="IMG3" />

***

## Usage in Avid Pro Tools

### Step 1 – Launch Pro Tools

Open the **Avid Pro Tools** app and drag an audio file into the Pro Tools timeline.

> 💡 *Hint:* Highlight the region of audio you wish to anonymize.
>
> <img alt="IMG5" />

### Step 2 – Open the Plugin

Navigate to **AudioSuite → Other → Voice Harbor**.

<img alt="IMG5" />

### Step 3 – Add Your Token

Paste your **developer token** into the plugin window.

> 💡 *Hint:* If you don’t have a token, click the ⚙️ icon next to the input box to open [voiceharbor.ai](https://voiceharbor.ai) and generate one.\\
>
> <img alt="IMG6" />

### Step 4 – Configure Redaction Parameters

Use the dropdowns to choose:

* **Language**
* **Gender**
* **Age**
* **Emotion**
* **Model**

Then click **Render** to anonymize the selected segment.\\

<img alt="IMG7" />

> 💡 *Hint:* The number beside **Render** controls the “collar” (extra buffer) around your selection.\
> Set to `0` if you want only your selected segment to be anonymized.

### Step 5 – Review the Output

A new anonymized clip appears in the **Clips** sidebar.\\

<img alt="IMG9" />

You can drag it into the timeline and listen to the result.

> 💡 *Hint:* You can render again if you wish to retry with different parameters — each anonymization will create a new clip in your **Clips** list.

***

## Plugin Parameters

<ResponseField name="biometric-age" type="string">
  Biometric age group to apply to the anonymized voice identity. Only used when `avatar` is not provided.
  Allowed values:

  * young-adult (18–39)
  * middle-aged-adult (40–59)
  * senior-adult (60+)
  * same
  * random
</ResponseField>

<ResponseField name="gender" type="string">
  Target gender of the anonymized voice identity.
  Allowed values:

  * same
  * opposite
  * random
  * f
  * m
</ResponseField>

<ResponseField name="language" type="string">
  Target language of the audio file.
  Allowed values:

  * en
  * fr
  * it
  * es
  * de
</ResponseField>

<ResponseField name="model_id" type="string">
  Model variant for biometric voice print redaction.
  Allowed values:

  * mini 0.25 RTF
  * advanced 0.75 RTF
</ResponseField>

<ResponseField name="emotion" type="string">
  Optional emotion to apply to anonymised identity.

  * happy
  * default
  * sad
</ResponseField>

***

## Compatibility (AAX Plugin)

| Component            | Requirement                |
| -------------------- | -------------------------- |
| **Host**             | Pro Tools 2024.10 or later |
| **Operating System** | macOS Sequoia 15 or later  |
| **Architecture**     | Apple Silicon and Intel    |

### Cloud-connected processing

🔌 Requires an active internet connection to communicate with VoiceHarbor.ai API for anonymization.


# Voice Harbor API
Source: https://docs.nijta.com/BuildwithVoiceHarbor/VoiceHarborAPI

Integrate Voice Harbor into your application using a developer usage token.

## Voice Harbor API

Use the Voice Harbor API to integrate biometric voice redaction into your own product or workflow.

This page is for **API usage only**.\
If you are using the Voice Harbor dashboard or playground, refer to the platform documentation instead.

***

## Authentication

API requests require a valid developer usage token.

Include it in the `Authorization` header:

```bash theme={null}
-H "Authorization: Bearer YOUR_USAGE_TOKEN"
```

***

## Processing Modes

Voice Harbor supports both **synchronous** and **asynchronous** API processing.

### Synchronous jobs

Short audio files are typically processed synchronously and may return immediately in the response.

### Asynchronous jobs

Longer audio files are processed asynchronously.

When a job is handled asynchronously:

* the job is accepted first
* processing continues after submission
* the result becomes available in the **Jobs** area when processing is complete

Async API jobs are associated with the account behind the developer token.

***

## Example API Usage

### Minimal biometric redaction request

```bash theme={null}
curl -X POST https://voiceharbor.ai/api/speech-to-speech-biometric-redaction \
  -H "Authorization: Bearer YOUR_USAGE_TOKEN" \
  -F "source_audio=@./martin.wav;type=audio/wav" \
  --output result.wav
```

### Custom biometric redaction request

```bash theme={null}
curl -X POST https://voiceharbor.ai/api/speech-to-speech-biometric-redaction \
  -H "Authorization: Bearer YOUR_USAGE_TOKEN" \
  -F "source_audio=@./martin.wav;type=audio/wav" \
  -F "model_id=advanced" \
  -F "age=same" \
  -F "gender=opposite" \
  -F "emotion=sad" \
  -F "language=fr" \
  --output redacted_fr.wav
```

***

## API Parameters

<ResponseField name="age" type="string">
  Biometric age group to apply to the anonymized voice identity. Only used when `avatar` is not provided.

  Allowed values:

  * young-adult (18–39)
  * middle-aged-adult (40–59)
  * senior-adult (60+)
  * same
  * random
</ResponseField>

<ResponseField name="gender" type="string">
  Target gender of the anonymized voice identity.

  Allowed values:

  * same
  * opposite
  * random
  * f
  * m
</ResponseField>

<ResponseField name="language" type="string">
  Target language of the audio file.

  Allowed values:

  * en
  * fr
  * it
  * es
  * de
</ResponseField>

<ResponseField name="model_id" type="string">
  Model variant for biometric voice print redaction.

  Allowed values:

  * mini 0.25 RTF
  * advanced 0.75 RTF
</ResponseField>

<ResponseField name="emotion" type="string">
  Optional emotion to apply to the anonymised identity.

  Allowed values:

  * happy
  * default
  * sad
</ResponseField>

***

## Audio Input Requirements

To ensure reliable processing and accurate biometric redaction, uploaded audio files must meet the following requirements.

### Supported File Formats

* **Guaranteed input support:** WAV & MP3 (`.wav`, `.mp3`),
* **Output:** WAV (`.wav`)

***

### File Size Limits

* **Maximum file size:** **10 MB per request**
* Files exceeding this limit will be rejected with a `413 Payload Too Large` error

> If you need higher limits for enterprise use cases, please contact support.

***

### Audio Duration Limits

* **Minimum duration:** more than 0 seconds
* **Maximum duration:** **60 minutes (3600 seconds)**

Files longer than 60 minutes are not accepted, even if they meet the file size limit.

***

## Result Delivery

How you receive results depends on the size and duration of the file:

* **Short files** may return immediately in the API response
* **Longer files** are processed asynchronously
* **Async results** are available from the **Jobs** area after processing completes

***


# Home
Source: https://docs.nijta.com/doc

Welcome to the Voice Harbor API documentation.

## Voice Harbor

Explore the robust tools Voice Harbor offers for transforming audio data.

<CardGroup>
  <Card title="🌍 Multilingual">
    English, German, French, Italian, and Spanish.
  </Card>

  <Card title="🎛️ Attribute Control">
    Modify or preserve gender, age group, and emotion after anonymization.
  </Card>

  <Card title="⚡ Low Latency">
    \~0.25× real-time processing speed for fast workflows.
  </Card>

  <Card title="🎧 Production Quality">
    Broadcast-grade output for post and live pipelines.
  </Card>

  <Card title="🛡️ Compliance">
    GDPR, EU AI Act, HIPAA, and CCPA-ready anonymization.
  </Card>
</CardGroup>

## Get Started

<CardGroup>
  <Card title="Biometric Redaction" icon="user-shield" href="https://docs.nijta.com/Biometric">
    Automatically redact biometric identifiers from audio for privacy compliance.
  </Card>

  <Card title="Voice Harbor API" icon="newspaper" href="https://docs.nijta.com/BuildwithVoiceHarbor/VoiceHarborAPI">
    Learn how to design the job parameters to fit your conversation scenario.
  </Card>
</CardGroup>

<CardGroup>
  <Card title="Access Token" icon="key" href="https://voiceharbor.ai">
    Automatically redact biometric identifiers from audio for privacy compliance.
  </Card>

  <Card title="Access Plugins" icon="key" href="https://voiceharbor.ai">
    Automatically redact biometric identifiers from audio for privacy compliance.
  </Card>
</CardGroup>