[title] ElevateAI Postman Collection
[path] /


[title] Submit an Interaction
[path] /


[title] Declare a Chat Interaction
[path] Submit an Interaction/


[title] Declare a Transcript
[path] Submit an Interaction/


[title] Check the Processing Status
[path] Check the Status/


[title] Upload an Audio File
[path] Submit an Interaction/Declare an Audio Interaction/


[title] Get Punctuated Transcript
[path] Retrieve Results/


[title] Getting Started
[path] /


[title] Declare an Audio Interaction
[path] Submit an Interaction/


[title] Echo Model Supported Languages
[path] Submit an Interaction/

The **Echo model** delivers a significant leap in transcription accuracy – outperforming the original CX model by up to **40% **and ensuring superior quality across a wide range of use cases.

To use Echo, include the body parameter `model` in your `POST /declare` request and set its value to `echo`.

Below is the complete list of **languages and dialects currently supported by Echo**.

<table isTableHeaderOn="true" selectedColumns="" selectedRows="" columnWidths="278,130,103">
  <tr>
    <td>
      <p><strong>Language</strong></p>
    </td>
    <td>
      <p><strong>Language Tag</strong></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Auto Language Detection</p>
    </td>
    <td>
      <p><code>auto</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>English</p>
    </td>
    <td>
      <p><code>en</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Spanish</p>
    </td>
    <td>
      <p><code>es-419</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>French</p>
    </td>
    <td>
      <p><code>fr</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>German</p>
    </td>
    <td>
      <p><code>de</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Portuguese</p>
    </td>
    <td>
      <p><code>pt</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Brazilian Portuguese</p>
    </td>
    <td>
      <p><code>pt-br</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Japanese</p>
    </td>
    <td>
      <p><code>ja</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Cantonese</p>
    </td>
    <td>
      <p><code>zh-YUE</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Mandarin</p>
    </td>
    <td>
      <p><code>zh-CMN</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Korean</p>
    </td>
    <td>
      <p><code>ko</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Italian</p>
    </td>
    <td>
      <p><code>it</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Thai</p>
    </td>
    <td>
      <p><code>th</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Russian</p>
    </td>
    <td>
      <p><code>ru</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Polish</p>
    </td>
    <td>
      <p><code>pl</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Indonesian</p>
    </td>
    <td>
      <p><code>id</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Swedish</p>
    </td>
    <td>
      <p><code>sv</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Czech</p>
    </td>
    <td>
      <p><code>cs</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Romanian </p>
    </td>
    <td>
      <p><code>ro</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Turkish </p>
    </td>
    <td>
      <p><code>tr</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Malay </p>
    </td>
    <td>
      <p><code>mi</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Catalan </p>
    </td>
    <td>
      <p><code>ca</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Hungarian </p>
    </td>
    <td>
      <p><code>hu</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Ukranian </p>
    </td>
    <td>
      <p><code>uk</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Greek </p>
    </td>
    <td>
      <p><code>el</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Bulgarian </p>
    </td>
    <td>
      <p><code>bg</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Arabic </p>
    </td>
    <td>
      <p><code>ar</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Serbian </p>
    </td>
    <td>
      <p><code>sr</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Macedonian </p>
    </td>
    <td>
      <p><code>mk</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Latvian </p>
    </td>
    <td>
      <p><code>lv</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Slovenian </p>
    </td>
    <td>
      <p><code>sl</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Hindi </p>
    </td>
    <td>
      <p><code>hi</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Danish </p>
    </td>
    <td>
      <p><code>da</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Dutch </p>
    </td>
    <td>
      <p><code>nl</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Urdu </p>
    </td>
    <td>
      <p><code>ur</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Slovak </p>
    </td>
    <td>
      <p><code>sk</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Hebrew </p>
    </td>
    <td>
      <p><code>he</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Finnish </p>
    </td>
    <td>
      <p><code>fi</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Norwegian </p>
    </td>
    <td>
      <p><code>no</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Azerbaijani </p>
    </td>
    <td>
      <p><code>az</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Lithuanian </p>
    </td>
    <td>
      <p><code>lt</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Estonian </p>
    </td>
    <td>
      <p><code>et</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Nynorsk </p>
    </td>
    <td>
      <p><code>nn</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Welsh </p>
    </td>
    <td>
      <p><code>cy</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Punjabi </p>
    </td>
    <td>
      <p><code>pa</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Afrikaans </p>
    </td>
    <td>
      <p><code>af</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Persian </p>
    </td>
    <td>
      <p><code>fa</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Basque </p>
    </td>
    <td>
      <p><code>eu</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Vietnamese </p>
    </td>
    <td>
      <p><code>vi</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Croatian </p>
    </td>
    <td>
      <p><code>hr</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Bengali </p>
    </td>
    <td>
      <p><code>bn</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Nepali </p>
    </td>
    <td>
      <p><code>ne</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Marathi </p>
    </td>
    <td>
      <p><code>mr</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Belarusian </p>
    </td>
    <td>
      <p><code>be</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Kazakh </p>
    </td>
    <td>
      <p><code>kk</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Armenian </p>
    </td>
    <td>
      <p><code>hy</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Swahili </p>
    </td>
    <td>
      <p><code>sw</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Tamil </p>
    </td>
    <td>
      <p><code>ta</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Albanian </p>
    </td>
    <td>
      <p><code>sq</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Bosnian </p>
    </td>
    <td>
      <p><code>bs</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Icelandic </p>
    </td>
    <td>
      <p><code>is</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Kannada </p>
    </td>
    <td>
      <p><code>kn</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Telugu </p>
    </td>
    <td>
      <p><code>te</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Maori </p>
    </td>
    <td>
      <p><code>mi</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Gujarati </p>
    </td>
    <td>
      <p><code>gu</code></p>
    </td>
  </tr>
  <tr>
    <td>
      <p>Mongolian </p>
    </td>
    <td>
      <p><code>mn</code></p>
    </td>
  </tr>
</table>


[title] Retrieve Declared Parameters
[path] Check the Status/


[title] Retireve Results
[path] /


[title] Untitled
[path] Generative AI/


[title] Untitled
[path] Generative AI/


[title] CX AI Features
[path] Overview/

# //  Overview

Modern consumers expect **seamless, efficient digital experience**s, and every interaction contributes to overall customer satisfaction. To meet these experiences, organizations need tools that deliver **deep, actionable insights** into customer conversations.

Powered by **NiCE's CX AI models** – and backed by decades of contact center research and billions of real-world interactions –  ElevateAI provides **immediate analysis of voice and chat data at scale** using pre-built behavioral models.




What's New&#x20;


With [**ElevateAI v1.11**](https://docs.elevateai.com/changelog), all declared interactions – [**Declare an Audio Interaction**](docId\:PqLj1vqO7gTf0iqj1LBVN), [**Declare a Chat Interaction**](docId\:iD41ifX7uC0RZDlb7RbtO), and [**Declare a Transcript**](docId:8OMp8XUfyRY9gaB1YIvul) – are now automatically processed through the full range of **CX AI services**.

This release expands coverage across all communication types and ensures **consistent, end-to-end customer experience analysis**.

Key Capabilities


ElevateAI's **pre-built CX AI models** make it easy to integrate intelligence into applications and workflows, unlocking faster time-to-value (TTV):

- **Automated interaction analysis** at enterprise scale
- **Predictive and prescriptive insights&#x20;**&#x70;owered by behavioral models
- **Purpose-built models** for immediate deployment and measurable impact

***

# Voice Activity

:::::VerticalSplit{layout}
::::VerticalSplitItem
For any audio interaction, **Voice Activity Segments** returned with [**Get CX AI**](docId:05yDvE34Wjax0rFhFWDxM) include **start and stop times (in milliseconds)** for both **voice** and **silence** periods. This enables immediate insight into **non-interaction time** – such as hold time or extended silence – when participants are not actively engaging.&#x20;

In addition, ElevateAI provides **speaker diarization** for CX AI results using both the **CX** and **Echo** transcription models. Each voice segment is automatically associated with **participantOne&#x20;**&#x6F;r **participantTwo**, giving you visibility into:

- **Total talk time** per speaker
- **Cross-talk detection** (when both participants speak simultaneously)
- **Initiator identification** (who spoke first during cross-talk)


:::hint{type="info"}
**NOTE:** The **CX model** supports diarization for both **Mono (single-channel)** and **Stereo (dual-channel)** audio. The **Echo model** currently supports diarization for **Stereo (dual-channel)** only.
:::


::::

::::VerticalSplitItem
:::CodeblockTabs
Sample CX AI Response

```json
{
    "allParticipants:" {
        ... 
        "voiceActivitySegments": [
            {
                "startTimeOffset": 0,
                "endTimeOffset": 4920,
                "result": "VOICE"
            },
            {
                "startTimeOffset": 4920,
                "endTimeOffset": 7560,
                "result": "SILENCE"
            }
            ... 
        ]
    }
    ... 
}
```
:::
::::
:::::

***

# &#x20;Enlighten AI Bundles

[**NiCE Enlighten Scores**](https://www.elevateai.com/ai-models/) are generated for each behavioral model and provided both as an **overall score** and as **quartile-based scores** (segmented by interaction stage). This allows users to track behavioral shifts over the course of a conversation and pinpoint when key behaviors occur.

## Behaviors for Customer Satisfaction

:::ExpandableHeading
## Acknowledge Loyalty

The **Acknowledge Loyalty** score imeasures how effectively an agent acknowledges a caller's long-term relationship with the organization and expresses appreciation for their loyalty.&#x20;

- **Higher scores** indicate the agent consistently recognizes customer tenure in a natural, conversational way.
- The model evaluates the **entire conversation**, using language from both the agent and the customer.
- For the most accurate results, use the `allParticipants` score, which reflects the interaction as a whole.
:::

:::ExpandableHeading
## Active Listening

The **Active Listening** score reflects how well an agent listens and responds throughout a conversation.

- **Higher scores** indicate that the agent is engaged, responsive, and avoids asking the customer to repeat information unnecessarily.
- The model evaluates language from **both agent and customer** to assess listening behavior.
- For the most accurate results, use the `allParticipants `score, which reflects the interaction as a whole.
:::

:::ExpandableHeading
##  Be Empathetic

The **Be Empathetic** score reflects how well an agent acknowledges the caller's issues and demonstrates understanding of their impact or hardship.

- **Higher scores&#x20;**&#x69;ndicate stronger predicted proficiency in showing empathy during conversations.
- The model evaluates **both agent and customer language** to assess empathetic behavior.
- For the most accurate results, use the `allParticipants` score, which reflects the interaction as a whole.
:::

:::ExpandableHeading
## Build Rapport

The **Build Rapport&#x20;**&#x73;core measures how effectively an agent creates a personal connection with the caller by engaging in **friendly, general conversation** outside the main issue.

- **Higher scores** indicate strong proficiency in building trust and comfort through small talk or positive interaction.
- The model analyzes **both agent and customer input** to assess rapport-building behavior.
- For the most accurate results, use the `allParticipants` score, which reflects the interaction as a whole.
:::

:::ExpandableHeading
## Demonstrate Ownership

The **Demonstrate Ownership&#x20;**&#x73;core measures how well an agent shows understanding of the caller's issue and a commitment to resolving it.

- **Higher scores** indicate strong proficiency in providing reassurance and taking responsibility.
- The model evaluates **both sides of the conversation** to assess ownership behaviors.
- For the most accurate results, use the `allParticipants` score, which reflects the interaction as a whole.
:::

:::ExpandableHeading
## Effective Questioning

The **Effective Questioning&#x20;**&#x73;core reflects how well an agent asks **thoughtful, purposeful questions** to better understand the caller's experience, concerns, or needs.

- **Higher scores** indicate stronger proficiency in uncovering issues and opportunities through meaningful questions.
- The model analyzes **agent and caller exchanges** across the full conversation.
- For the most accurate results, use the **allParticipants** score, which reflects the interaction as a whole.
:::

:::ExpandableHeading
## &#x20;Inappropriate Action

The **Inappropriate Action** score reflects how well an agent avoids unprofessional or offensive behaviors – such as refusing a reasonable transfer request, using inappropriate language, or showing disrespect.&#x20;

- **Higher scores** indicate stronger proficiency in consistently maintaining professional conduct.
- The model analyzes **both agent and customer language** to evaluate this behavior.
- For the most accurate results, use the `allParticipants` score, which reflects the interaction as a whole.
:::

:::ExpandableHeading
## Promote Self-Service

The **Promote Self-Service** score measures how effectively an agent encourages customers to use available self-service options – such as an IVR system, website, or mobile app – when appropriate.&#x20;

- **Higher scores** indicate strong proficiency in guiding customers toward tools that can streamline future interactions.
- The model evaluates **language from both agent and customer** to assess this behavior.
- For the most accurate results, use the `allParticipants` score, which reflects the interaction as a whole.
:::

:::ExpandableHeading
## Sentiment

The **Sentiment** score predicts the likelihood that a customer would give &#x61;**&#x20;positive post-interaction rating** in a survey.

- The score is derived from both **spoken language** (*what* was said) and **acoustic cues** (*how&#x20;*&#x69;t was said), including pitch, tone, laughter detection, and cross-talk.
- The model analyzes the **full conversation** across both agent and customer to determine customer sentiment.
- For the most accurate results, use the `allParticipants` score, which reflects the interaction as a whole.
:::

:::ExpandableHeading
## Set Expectations

The **Set Expectations&#x20;**&#x73;core measures how effectively an agent communicates **next steps**, outlines **required actions**, and ensures the customer understands what to expect after the interaction.

- **Higher scores** indicate strong proficiency in providing clear, proactive guidance that builds confidence and reduces uncertainty.
- The model evaluates **language from both agent and customer&#x20;**&#x74;o assess this behavior.
- For the most accurate results, use the `allParticipants` score, which reflects the interaction as a whole.
:::

## Vulnerable Customer Behaviors

A **Vulnerable Customer** is defined by the UK Financial Conduct Authority (FCA) as:

*"Someone who, due to their personal circumstances, is especially susceptible to harm, particularly when a firm is not acting with appropriate levels of care."*

These customers may require additional support or actions from organizations to ensure they receive **fair, equitable, and appropriate service**. Built by NiCE, ElevateAI's **Vulnerable Customer models** help identify potential signals of vulnerability in real-time interactions.

:::ExpandableHeading
## Vulnerable Customer

The **Vulnerable Customer&#x20;**&#x73;core predicts the likelihood that a caller may fall into one or more of the five subcategories commonly referenced in contact centers:**&#x20;health, life events, resilience, capability, and age-related factors.**

- **Higher scores** suggest customer language or behaviors that may signal potential vulnerability.
- The model evaluates **both agent and customer language** across the interaction.
- For the most accurate results, use the `allParticipants` score, which reflects the conversation as a whole.
:::

:::ExpandableHeading
## &#x20;Vulnerable Capability

The **Vulnerable Capability&#x20;**&#x73;core predicts the likelihood that a customer has **limited knowledge, confidence, or skills** in managing financial matters. This may also reflect challenges in areas such as **financial literacy or digital skils**.&#x20;

- **Higher scores** indicate the customer may require extra support to navigate the interaction effectively.
- The model analyzes **both agent and customer input** to identify signals of limited capability.
- For the most accurate results, use the `allParticipants` score, which reflects the conversation as a whole.
:::

:::ExpandableHeading
## Vulnerable Health

The **Vulnerable Health** score predicts the likelihood that a customer is experiencing **physical health conditions or illnesses** that impact their ability to manage daily activities or interactions.

- **Higher scores** suggest the customer may require additional assistance due to health-related challenges.
- The model evaluates **both agent and customer language** throughout the interaction.
- For the most accurate results, use the `allParticipants` score, which reflects the conversation as a whole.
:::

:::ExpandableHeading
## Vulnerable Life Event

The **Vulnerable Life Event&#x20;**&#x73;core predicts the likelihood that a customer is undergoing significant **life changes or hardships**, such as bereavement, job loss, or relationship breakdown.

- **Higher scores** indicate the customer may need additional care and support during the interaction.
- The model analyzes **language from both agent and customer** to identify potential signals.
- For the most accurate results, use the `allParticipants `score, which reflects the conversation as a whole.
:::

:::ExpandableHeading
## Vulnerable Mental Health

The **Vulnerable Mental Health&#x20;**&#x73;core predicts the likelihood that a customer is experiencing **mental health challenges&#x20;**&#x74;hat may affect their ability to manage daily activities or decision making.

- **Higher scores** suggest the customer may require additional support or accomodations.
- The model evaluates **both agent and customer language** to identify relevant indicators.
- For the most accurate results, use the `allParticipants` score, which reflects the conversation as a whole.
:::

:::ExpandableHeading
## Vulnerable Resilience

The **Vulnerable Resilience** score predicts the likelihood that a customer has a **reduced ability to cope** with financial or emotional stress.

- **Higher scores** indicate the customer may need extra support due to difficulty managing stress or pressure.
- The model evaluates **both agent and customer language** to detect signals of reduced resilience.
- For the most accurate results, use the`  allParticipants  `score, which reflects the conversation as a whole.
:::

***

Additional models in currently in **beta** include:

- **FInancial Distress**
- **High-Risk Transactions**

For the most up-to-date details on new models and features, [**visit the ElevateAI Release Notes**](https://docs.elevateai.com/changelog).&#x20;

**Need more help?** Contact the [**ElevateAI Support team**](mailto\:support@elevateai.com).&#x20;

[title] Overview
[path] /

# //  Introduction

**ElevateAI APIs** bring the best of **AI, ASR, and NLP** to your contact center – transforming conversations into accurate transcripts and actionable insights.

With ElevateAI, you can:

- **Transcribe conversations** with enterprise-grade accuracy
- **Analyze interactions at scale** using CX AI models for sentiment, satisfaction, and compliance
- **Activate intelligence instantly** with our Generative AI Feature Suite, including:
  - AutoSummary
  - Agent Coaching Assistant
  - Ask ElevateAI Q\&A
  - ... and more!

ElevateAI lets you access key data necessary to ***understand conversations at scale****.*&#x20;

![ElevateAI API Information Flow](https://archbee-image-uploads.s3.amazonaws.com/1M04sW8luRoDRHuWICG7y/uDt7j_nrR8UJLdZ0oEIHm_image.png "NiCE ElevateAI API Information Flow")



:::hint{type="success"}
**NEW:** **ElevateAI Echo**

Meet Echo, ElevateAI's next generation transcription model – now available for enterprise use.

Built for **high-accuracy speech recognition at scale**, Echo supports **50+ languages and dialects** with regional accent optimization, making it ideal for global applications.

**With Echo, enterprises gain:**

- **Advanced transcription accuracy** for complex conversations
- **Multilingual support** tuned for diverse regional accents
- **Scalable performance** to handle high-volume workflows with ease

🔗 [**Echo Model Supported Languages**](docId:6umizpOXhj2fcFgGarHy_)


:::

# //  Just Getting Started?

[**Getting Started**](docId\:MCxT9ad7ZH7V59fXPy_7I) in under 60 seconds!&#x20;

Each [**API Endpoint**](https://docs.elevateai.com/tutorials/getting-started#E8Prs) includes a detailed `tutorial` with required parameters, code samples, and response examples/schemas to help with your integration quickly and efficiently.

# //  Not a Developer?

You can transcribe and analyze `audio` interactions directly from the web-based ElevateAI portal, using our [**No-Code Dashboard**](https://docs.elevateai.com/tutorials/elevateai-dashboards#rVou-)! &#x20;


:::hint{type="info"}
We're here to help!

If you have any questions, our [**team of product experts and developers**](https://docs.elevateai.com/#4zATw) are available to provide [**additional information and support**](https://docs.elevateai.com/#4zATw)!&#x20;
:::

***

# Authentication

Your **active API tokens** are used to authenticate requests on behalf of your account and grant access to a wide range of privileges. To protect your data and systems:

- **Keep your tokens secure** at all times
- **Never share API tokens** in publicly accessible locations, including:
  - Public GitHub repositories
  - Client-side code
  - Forums or documentation

🔒 **Treat API tokens like passwords** – exposing them can compromise your account.


:::hint{type="info"}
**NOTE:** To ensure authentication, all API requests must be made over HTTPS. Requests made over HTTP and/or API requests without an active API token will fail.
:::


For your convenience and security, API tokens can be managed at any time using the [**ElevateAI Manage Tokens Dashboard**](https://docs.elevateai.com/tutorials/elevateai-dashboards#_xQWv).

***

# //  Data Retention & Security

With ElevateAI, **your data is yours**!

:::hint{type="info"}
**API Security**

The **ElevateAI API** is secured using **Transport Layer Security (TLS) 1.2**, which encrypts all communication and protects data in transit.&#x20;


To further enhance security, the service also **supports TLS mutual authentication**, ensuring that only authorized clients can access the API.
:::

****

**All source data is deleted promptly upon processing**. Analysis output is stored in our US-based data warehouse for up to 60 days, encrypted in transit and at rest, so that you may access your results.&#x20;

**NOTE:** After 60 days, ***all associated data is deleted and irretrievable***.

If you have retrieved the desired results and would like to permanently delete all analysis data from our database prior to the 60-day standard retention period, you may do so *at any time* using the [**Delete Data**](docId\:Y_2_7nFL0UauuE05mJsX0).

As a publicly traded company trusted by leading brands worldwide, we make data security a **top priority**.&#x20;

For additional information, please refer to the [**Privacy Notice**](docId\:wkBbQ_Cf50IsO6zmqRcOk).

***

# //  Processing Times

Remember, you can **retrieve the processing status of your interaction** at any time directly from a `GET`[**Check the Processing Status**](docId\:dg0fHnxsBeEqTYD1ruQrQ) or the [**ElevateAI Dashboards**](docId\:OZqMg2TQPCYBJjddHBrOU).&#x20;

## Audio Files

- **Post-Call&#x20;**`Audio` interactions are **generally processed within \~2% of the total file duration.**
- **Real-Time&#x20;**`Audio` interactions are **generally processed in \~600-1200 ms.**

## Transcript and Chat Files

- [**Declare a Chat Interaction**](docId\:iD41ifX7uC0RZDlb7RbtO) and [**Declare a Transcript**](docId:8OMp8XUfyRY9gaB1YIvul) interactions are **generally processed in seconds.**


**NOTE**: Processing time across all file types – `Audio`, `Chats`, and `Transcriptions` – may vary due to your system integration configuration and the number of concurrent requests.

***

# //  Accepted File Formats & Sizes

## Audio File Formats

ElevateAI supports all unencrypted audio types, whether single or dual channel.

If you have questions or would like to see a full list of supported audio file types,  contact the [**ElevateAI Support Team**](https://docs.elevateai.com/#4zATw).


:::hint{type="info"}
&#x20;**Pro Tip**: For highest levels of accuracy, we suggest using stereo G.729A audio files.
:::


Supported File Sizes
--------------------

ElevateAI supports both uploads and download&#x73;**&#x20;up to 450MB**.

***

# Transcription Models & Language Capabilities

## What's New?

Introducin&#x67;**&#x20;ElevateAI Echo** – our newest, fastest, and most accurate transcription model. Echo is now available for enterprise use, supporting both **real-time** and **post-call** transcription.

## //  Next-Gen Echo Transcription Model&#x20;

Our **Echo transcription model** is designed for **high-accuracy speech recognition at scale**, delivering up to **40% accuracy improvements** in benchmark testing. Echo supports **50+ languages and dialects** with automatic language detection, making it a powerful solution for global applications.&#x20;

**Built for enterprise needs, Echo provides:&#x20;**

- **High transcription accuracy** for complex and industry-specific conversations
- **Multilingual support&#x20;**&#x77;ith optimization for diverse regional accents
- **Scalable performance** to handle high-volume workflows without compromise
- **Flexible deployment options**, including real-time and post-call transcription

🔗 [**Echo Model Supported Languages**](docId:6umizpOXhj2fcFgGarHy_)

Echo is ideal for a wide range of media types – includin&#x67;**&#x20;interviews, podcasts, videos, and calls** – and is further optimized for **Contact Center audio**!

## //  Purpose-Built CX Transcription Model  

The **CX transcription model** was purpose-built for the contact center, drawing on decades of industry expertise and billions of real customer interactions. It delivers **high-accuracy transcription** optimized for complex, multi-speaker conversations, achieving a **Word Error Rate (WER) below 10%.**

Designed for **cost-efficiency** and **seamless integration**, the CX model powers advanced customer sentiment analysis, enabling enterprises to strengthen compliance, enhance quality assurance, and improve customer experience outcomes.

**Built for enterprise contact centers, the CX model provides:**

- **High-accuracy transcription** tailored to customer service interactions
- **Advanced speaker diarization** with robust multi-speaker handling
- **Real-time insights** driven by sentiment and behavioral analytics

The CX model supports all types of contact center media, delivering **affordable, scalable transcription** that fuels deeper CX intelligence and operational efficiency.

# //  Language Support & Model Capabilities

## Languages: CX Model

Our **CX Model&#x20;**&#x73;upports the following languages:

<table isTableHeaderOn="true" selectedColumns="" selectedRows="" columnWidths="280,109,103">
  <tr>
    <td>
      <p><strong>Language</strong></p>
    </td>
    <td>
      <p><strong>Language Tags</strong></p>
    </td>
    <td>
      <p><strong>PII Redaction</strong></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>North American English</strong></p>
    </td>
    <td>
      <p><code>en-us</code></p>
    </td>
    <td>
      <p><strong>Social Security numbers; Credit Card numbers; CVV/CVC numbers</strong></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>International English</strong></p>
    </td>
    <td>
      <p><code>en</code></p>
    </td>
    <td>
      <p><strong>Credit Card numbers; CVV/CVC numbers</strong></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>Latin American Spanish</strong></p>
    </td>
    <td>
      <p><code>es-419</code></p>
    </td>
    <td>
      <p><strong>Social Security numbers; Credit Card numbers; CVV/CVC numbers</strong></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>French</strong></p>
    </td>
    <td>
      <p><code>fr</code></p>
    </td>
    <td>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>German</strong></p>
    </td>
    <td>
      <p><code>de</code></p>
    </td>
    <td>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>Brazilian</strong></p>
    </td>
    <td>
      <p><code>pt-br</code></p>
    </td>
    <td>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>Japanese</strong></p>
    </td>
    <td>
      <p><code>ja</code></p>
    </td>
    <td>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>Cantonese</strong></p>
    </td>
    <td>
      <p><code>zh-YUE</code></p>
    </td>
    <td>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>Mandarin</strong></p>
    </td>
    <td>
      <p><code>zh-CMN</code></p>
    </td>
    <td>
    </td>
  </tr>
</table>

## Languages: Echo Model

Echo supports **50+ languages and dialects** with automatic language detection, making it a powerful solution for global applications.&#x20;

🔗 [**Echo Model Supported Languages**](docId:6umizpOXhj2fcFgGarHy_)



## Languages: CX AI Models

Our **CX AI models** generate reportable AI scores across key contact center metrics, including customer sentiment, satisfaction, and agent performance.

View the complete list of supported languages for CX AI models:

::::Tabs
:::Tab{title="Audio"}
<table isTableHeaderOn="true" selectedColumns="" selectedRows="" columnWidths="253,207,126">
  <tr>
    <td>
      <p><strong>Language</strong></p>
    </td>
    <td>
      <p><strong>Language Tag</strong></p>
    </td>
    <td>
      <p><strong>CX AI Models</strong> </p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>North American English</strong></p>
    </td>
    <td>
      <p><code>en-us</code></p>
    </td>
    <td>
      <p><a href="https://docs.elevateai.com/cx-ai-features#nIOo8">****</a>; <strong>Sales Effectiveness</strong></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>International English</strong></p>
    </td>
    <td>
      <p><code>en</code></p>
    </td>
    <td>
      <p><a href="https://docs.elevateai.com/cx-ai-features#nIOo8">****</a>; <a href="https://docs.elevateai.com/cx-ai-features#nIOo8">****</a></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>Latin American Spanish</strong></p>
    </td>
    <td>
      <p><code>es-419</code></p>
    </td>
    <td>
      <p><a href="https://docs.elevateai.com/cx-ai-features#nIOo8">****</a></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>Brazilian Portuguese</strong></p>
    </td>
    <td>
      <p><code>pt-br</code></p>
    </td>
    <td>
      <p><a href="https://docs.elevateai.com/cx-ai-features#nIOo8">****</a></p>
    </td>
  </tr>
</table>


:::

:::Tab{title="Transcript"}
<table isTableHeaderOn="true" selectedColumns="" selectedRows="" columnWidths="225,168,126">
  <tr>
    <td>
      <p><strong>Language</strong></p>
    </td>
    <td>
      <p><strong>Language Tag</strong></p>
    </td>
    <td>
      <p><strong>CX AI Models</strong></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>North American English</strong></p>
    </td>
    <td>
      <p><code>en-us</code></p>
    </td>
    <td>
      <p>****<a href="https://docs.elevateai.com/cx-ai-features#nIOo8">****</a><strong>; Sales Effectiveness</strong></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>International English</strong></p>
    </td>
    <td>
      <p><code>en</code></p>
    </td>
    <td>
      <p><a href="https://docs.elevateai.com/cx-ai-features#nIOo8">****</a>; <a href="https://docs.elevateai.com/cx-ai-features#nIOo8">****</a></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>Latin American Spanish</strong></p>
    </td>
    <td>
      <p><code>es-419</code></p>
    </td>
    <td>
      <p><a href="https://docs.elevateai.com/cx-ai-features#nIOo8">****</a></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>Brazilian Portuguese</strong></p>
    </td>
    <td>
      <p><code>pt-br</code></p>
    </td>
    <td>
      <p><a href="https://docs.elevateai.com/cx-ai-features#nIOo8">****</a></p>
    </td>
  </tr>
</table>
:::

:::Tab{title="Chat"}
<table isTableHeaderOn="true" selectedColumns="" selectedRows="" columnWidths="253,172,126">
  <tr>
    <td>
      <p><strong>Language</strong></p>
    </td>
    <td>
      <p><strong>Language Tag</strong></p>
    </td>
    <td>
      <p><strong>CX AI Models</strong></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>North American English</strong></p>
    </td>
    <td>
      <p><code>en-us</code></p>
    </td>
    <td>
      <p>****<a href="https://docs.elevateai.com/cx-ai-features#nIOo8"><strong>Behaviors for CSAT</strong></a>; Sales Effectiveness</p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>International English</strong></p>
    </td>
    <td>
      <p><code>en</code></p>
    </td>
    <td>
      <p><a href="https://docs.elevateai.com/cx-ai-features#nIOo8"><strong>Behaviors for CSAT</strong></a></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>Latin American Spanish</strong></p>
    </td>
    <td>
      <p><code>es-419</code></p>
    </td>
    <td>
      <p><a href="https://docs.elevateai.com/cx-ai-features#nIOo8"><strong>Behaviors for CSAT</strong></a></p>
    </td>
  </tr>
</table>
:::
::::

## Languages: Generative AI

Our **Generative AI endpoints** support all languages available in the **Echo transcription model.&#x20;**

🔗 [**Echo Model Supported Languages**](docId:6umizpOXhj2fcFgGarHy_)

Generative AI endpoints can be invoked in real time:&#x20;

- Declare --> for chats and transcripts.

:::BlockQuote
**NOTE:** Audio files must be fully processed before they can be submitted for Generative AI analysis.
:::

***

# //  Error Handling

ElevateAI uses conventional HTTP response codes for each API request.

- Codes in the `2xx` range indicate the request was successfully executed.
- Codes in the `4xx` range indicate a failure based on the information provided, e.g., a required parameter was omitted.
- While rare, codes in the `5xx` range may indicate an error with the ElevateAI service.

If a request is successful but an error occurs when uploading, downloading, or processing your interaction, a descriptive `errorMessage ` will be provided when [**Check the Processing Status**](docId\:dg0fHnxsBeEqTYD1ruQrQ) of your interaction.


:::hint{type="info"}
**Need Additional Assistance?**

Visit the [**ElevateAI FAQ**](https://www.elevateai.com/faq/) for more information – or [**contact the ElevateAI team**](https://docs.elevateai.com/#4zATw)  – for additional help and expert guidance, tailored to your needs.

Can't find what you're looking for across our documentation? Our [**team of product specialists and engineers**](https://docs.elevateai.com/#4zATw) is always here to help.

**Still Need Help?** Contact the [**ElevateAI Support team**](mailto\:support@elevateai.com).&#x20;

:::

<table columnWidths="330,331" selectedRows="" isTableHeaderOn="true" selectedColumns="">
  <tr>
    <td>
      <p><strong>HTTP Status Code </strong></p>
    </td>
    <td>
      <p><strong>Summary</strong></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>400 – Bad Request</strong></p>
    </td>
    <td>
      <p>The API request does not contain the expected parameters – either missing a required parameter or providing an unexpected value for a parameter. Prior to re-requesting, review the parameters and code examples within <a href="https://docs.elevateai.com/tutorials#E8Prs"><strong>the associated tutorial</strong></a>. </p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>401  – Unauthorized</strong></p>
    </td>
    <td>
      <p>The API request is missing or passed an invalid <code>X-API-Token</code> in the header. Prior to re-requesting, confirm or request your API token within the <a href="https://docs.elevateai.com/tutorials/elevateai-dashboards#_xQWv"><strong>Manage Tokens Dashboard</strong></a>.</p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>404 – Not Found</strong></p>
    </td>
    <td>
      <p>Either the API request was made with an invalid/deleted <code>interactionIdentifier</code> in the path or analysis results have been requested prior to processing completion. Prior to re-requesting, confirm your API token within the <a href="https://docs.elevateai.com/tutorials/elevateai-dashboards#_xQWv"><strong>Manage Tokens Dashboard</strong></a> and <a><strong>Check the Processing Status</strong></a>. </p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>409 – Conflict</strong></p>
    </td>
    <td>
      <p>The API request made can't be completed because you have previously <a><strong>Upload an Audio File</strong></a> or provided a <code>downloadUrl</code> when <a><strong>Declare an Audio Interaction</strong></a>.</p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>413 – Payload Too Large</strong></p>
    </td>
    <td>
      <p>The ElevateAI service couldn't retrieve the uploaded file or the file is larger than  the <a href="https://docs.elevateai.com/#iZ75C"><strong>maximum supported file size</strong></a>. If you've <a href="https://docs.elevateai.com/#iZ75C"><strong>confirmed your file size</strong></a>, <a><strong>Upload an Audio File</strong></a> – and are still receiving an error? Re-declare your interaction.</p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>429 – Too Many Requests</strong></p>
    </td>
    <td>
      <p>The API request to declare the interaction exceeds the quota associated with your account. To upgrade to a paid account – or request that your quota be increased – <a href="https://docs.elevateai.com/#4zATw"><strong>contact our Sales and Partnerships team</strong></a>!  </p>
    </td>
  </tr>
</table>

***

# &#x20;Daily Quotas: Free & Paid Accounts

## Free Accounts: Introducing Fast Start

All users have access to **declare up to 10 free interactions per day** throug&#x68;**&#x20;ElevateAI's Fast Start program**!

The **Fast Start program** gives users ten (10) free interactions every day to explore our platform, no credit card required! With your free interactions, you can:

- Transcribe calls using our [**Transcription Features**](docId\:S9jOxP3aXKxPshr3ztM1j)
  - Test drive our newest offering: [**Real-Time API Documentation**](docId\:o_hjXU7Ra-ymCNvf5p52_)
- Unlock insights across [**CX AI Features**](docId\:ZATcqMNsVApZs9WWKgeCn) with [**Enlighten AI**](https://docs.elevateai.com/cx-ai-features#zHkYJ) and [**Get CX AI**](docId:05yDvE34Wjax0rFhFWDxM)
- Use our [**ElevateAI Explore dashboard and reporting tool**](https://www.elevateai.com/eai-explore/) for no-code reporting and analysis, using your data OR a sample data file!
- Try our [**ElevateAI Generative AI API calls**](docId\:y-mPGjLgd3oo9VOazv562), including [**AutoSummary**](https://docs.elevateai.com/tutorials/generative-ai-api-endpoint-details#61S73), [**Agent Coaching**](https://docs.elevateai.com/tutorials/generative-ai-api-endpoint-details#OtHuN), and [**Ask ElevateAI Q\&A**](https://docs.elevateai.com/tutorials/generative-ai-api-endpoint-details#IKGCp)

Have questions? Ready to upgrade to a paid account? Contact our [**Sales and Partnerships team**](https://docs.elevateai.com/#4zATw)!&#x20;

## Paid Accounts

By default, paid accounts have access to **declare up to 5,000 interactions per day**.

If you require a higher limit, please [**contact our Support Team**](https://docs.elevateai.com/#4zATw) to request a limit increase.

Learn more via [**ElevateAI Pricing&#x20;**](https://www.elevateai.com/pricing/)or [**Request a Quote**](https://www.elevateai.com/pricing/) for Enterprise Pricing and scalability!

***

# // Additional Support



Our team of product experts and developers are on call and here to help.&#x20;

For specific inquiries, please reach out to the appropriate team:



<table columnWidths="541,202" selectedRows="" selectedColumns="">
  <tr>
    <td align="right">
      <p><strong>Sales &#x26; Partnerships</strong>
      For enterprise pricing, high-volume packages, tailored quotes, or partnerships, contact:</p>
    </td>
    <td align="center">
      <p><a href="mailto:sales@elevateai.com">****</a></p>
    </td>
  </tr>
  <tr>
    <td align="right">
      <p><strong>Product &#x26; Technical</strong></p>
      <p>For questions about transcription capabilities, model performance, or upcoming releases, contact:</p>
    </td>
    <td align="center">
      <p><a href="mailto:support@elevateai.com">****</a></p>
    </td>
  </tr>
  <tr>
    <td align="right">
      <p><strong>Legal &#x26; Compliance</strong></p>
      <p>For inquiries about our Terms of Use, Privacy Policy, or other legal matters, contact:</p>
    </td>
    <td align="center">
      <p><a href="https://legal@elevateai.com">****</a></p>
    </td>
  </tr>
  <tr>
    <td align="right">
      <p><strong>General Support</strong></p>
      <p>For all other product, sales, or support-related questions, contact:</p>
    </td>
    <td align="center">
    </td>
  </tr>
</table>



**Need more help?** Contact the [**ElevateAI Support team**](mailto\:support@elevateai.com).&#x20;

[title] Check the Status
[path] /


[title] Untitled
[path] Overview/


[title] Untitled
[path] Overview/


[title] Transcription Features
[path] Overview/

# //  Introduction

**Accurate transcription** is essential for downstream analytics, making **speech-to-text (STT)** one of the most valuable capabilities in modern contact center solutions. Yet call center audio presents unique challenges – such as background noise, overlapping conversations, and telephony limitations that affect quality.

**NiCE ElevateAI&#x20;**&#x61;ddresses these challenges with decades of research and billions of real-world contact center interactions. Our platform deliver&#x73;**&#x20;high-accuracy conversational transcripts** through two purpose-built models:

- **CX Model** – optimized for contact center environments
- **Echo Model** – next-generation transcription for global, multilingual use cases

**Transcript formats available:**

- [**Get Phrase-by-Phrase Transcript**](docId\:Lb05bq-53XEiIWV5lXi9k)
- [**Get Punctuated Transcript**](docId\:ETiGRCBkICBUnyR5t0RYg)

This flexibility ensures seamless integration into **analytics**, **compliance**, and **customer experience (CX) workflows**.

# //  Transcription Models

## What's New

- **November 2024 →** We introduced **Echo**, our next-generation transcription model. Built for accuracy at scale, Echo delivers up to **40% higher accuracy** than our original CX model, ensuring superior transcription quality across a wide range of use cases.
- **July 2025 →&#x20;**&#x57;e expanded Echo with the launch of **Echo Real-Time Transcription**, enabling enterprises to capture conversations instantly with the same industry-leading accuracy.

Use our new [**Fast Start Program**](https://docs.elevateai.com/#iwwlY) to try Echo today – no contract, no credit card required. Explore both **real-time** and **post-call** transcription with 10 free interactions per day.

***

## Transcription Models at a Glance

**Choose the ElevateAI transcription model** that best suits your workflow:

<table isTableHeaderOn="true" selectedColumns="" selectedRows="" columnWidths="220,220,221">
  <tr>
    <td>
      <p><strong>Model</strong></p>
    </td>
    <td>
      <p><strong>Best For</strong></p>
    </td>
    <td>
      <p><strong>Key Strengths</strong></p>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>CX Model</strong></p>
    </td>
    <td>
      <p>Contact center environments</p>
    </td>
    <td>
      <ul>
      <li>Optimized for multi-speaker conversations</li>
      <li>&#x3C;10% WER on call center audio</li>
      <li>Real-time sentiment &#x26; compliance insights</li>
      </ul>
    </td>
  </tr>
  <tr>
    <td>
      <p><strong>Echo Model</strong></p>
    </td>
    <td>
      <p>Global, multilingual transcription</p>
    </td>
    <td>
      <ul>
      <li>40% accuracy improvement over benchmarks</li>
      <li>50+ languages &#x26; dialects with auto-detection</li>
      <li>Scales for high-volume workflows</li>
      </ul>
    </td>
  </tr>
</table>

- **When to use CX** → Customer service conversations, compliance/QA, and real-time insights monitoring
- **When to use Echo** → Multilingual transcription, global media (interviews, podcasts, videos), and enterprise workflows at scale



:::hint{type="info"}
**PRO TIP**: Many enterprises combine both models – using **Echo&#x20;**&#x66;or fast, accurate real-time transcription across global operations and **CX** for complex contact center interactions enriched with Enlighten AI and CX AI insights.
:::

## Selecting the Echo Model

To use the Echo Transcription model, add the body parameter `model` to your POST declare and set the value to `echo` when declaring an interaction.

:::hint{type="danger"}
**NOTE:** Currently, **the Echo model does not perform redaction**.&#x20;

Future releases will continue to move Echo towards feature parity with the CX transcription model; [**access the latest ElevateAI Release Notes**](https://docs.elevateai.com/changelog).
:::

## Switching Between Echo and CX Models

- Our original, purpose-built **CX model** can be used by omitting the model parameter or setting it to `cx`

# //  PII Redaction

**Personally Identifiable Information (PII)** such as social security numbers, credit card numbers, and CVV/CVC numbers is **automatically redacted** before a transcript is stored or returned.

:::hint{type="info"}
**IMPORTANT:** PII redaction is available **only with the CX transcription model**.

The Echo model does not currently support PII redaction, and any media processed with Echo will not be redacted.
:::

When retrieving either a [**Get Phrase-by-Phrase Transcript**](docId\:Lb05bq-53XEiIWV5lXi9k) or [**Get Punctuated Transcript**](docId\:ETiGRCBkICBUnyR5t0RYg), details on each redacted segment – including timing, type, and confidence score – are also returned.



:::::VerticalSplit{layout="middle"}
::::VerticalSplitItem


:::hint{type="info"}

**Remember:** All source data is deleted immediately and promptly upon processing. 

Please refer to our [**Data Retention & Security Guidelines**](https://docs.elevateai.com/overview#MYWqd) for additional details. uidelines for additional details.
:::


::::

::::VerticalSplitItem
:::CodeblockTabs
Sample Transcription Output

```json
{
    ...
    "redactionSegments": [
        {
        "startTimeOffset": 1467720,
        "endTimeOffset": 1468030
        "result": "CVV",
        "score": 0.98745
        },
        ...
    ]
}
```
:::
::::
:::::

***

# //  Speaker Labels

ElevateAI automatically associates each phrase in a transcript with a participant (**up to two speakers**) in both [**Get Phrase-by-Phrase Transcript**](docId\:Lb05bq-53XEiIWV5lXi9k) and [**Punctuated Transcript**](docId\:lUBKnfsfjJ9ZA79mM-kdN) transcript formats.&#x20;

## Speaker Diarization

With **Speaker Diarization**, ElevateAI distinguishes between participants in a conversation –  delivering cleaner transcripts and enabling more reliable analytics.

**CX Model →&#x20;**&#x53;upports automatic speaker diarization for both **Mono (single-channel)** and **Stereo (dual-channel)** audio inputs.

**Echo Model →&#x20;**&#x52;ecently expanded to support automatic diarization for **Stereo (dual-channel)&#x20;**&#x61;udio, with additional capabilities in progress to bring feature parity with the CX model.

The system distinguishes between speakers – labeling them as `participantOne` and `participantTwo` – and tags each phrase accordingly.

Key benefits of Speaker Diarization include:

- **Improved transcript clarity →&#x20;**&#x45;ach speaker's statements are clearly attributed, making transcripts easier to read and review.
- **Simplified post-processing →&#x20;**&#x41;ccurate labels enable downstream automation for analytics, summarization, and role assignment.
- **Enhanced compliance & QA →&#x20;**&#x43;lear speaker separation helps meet regulatory requirements and streamlines quality assurance workflows.

:::hint{type="info"}
**NOTE:** Diarization currently supports **two speakers** (participantOne, participantTwo) and is automatically applied when using supported models and audio formats.
:::

## Channel Labels

For **dual channel audio files** – e.g., a phone recording with the agent and customer on separate channels – ElevateAI automatically associates each phrase with the correct channel.

Using stereo recordings does **not affect processing speed or fees**, making it a flexible option for contact center workflows.

Leveraging stereo recordings *does not impact* processing speed or fees.

- [**View pricing information**](https://www.elevateai.com/pricing/)
- [**Learn more about audio, chat, and transcript processing times**](https://docs.elevateai.com/#CcDVe)

****

**Need more help?** Contact the [**ElevateAI Support team**](mailto\:support@elevateai.com).&#x20;

[title] Get CX AI
[path] Retrieve Results/


[title] Get Phrase-by-Phrase Transcript
[path] Retrieve Results/


[title] Untitled
[path] Generative AI/


[title] ElevateAI Dashboards
[path] Getting Started/


[title] Generative AI
[path] /


[title] Delete Data
[path] /