---
title: "Streaming recognition builder"
slug: "clovaspeech-builder-streaming"
updated: 2026-09-17T09:33:47Z
published: 2026-09-17T09:33:47Z
canonical: "guide.ncloud-docs.com/clovaspeech-builder-streaming"
stale: true
---

> ## Documentation Index
> Fetch the complete documentation index at: https://guide.ncloud-docs.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Streaming recognition builder

Available in Classic and VPC

Using the CLOVA Speech Builder, you can request and manage voice recognition tasks through a UI environment. Builders are provided per domain, and you can use the following menus within the Builder:

- **Task list** menu: Register and manage recognition tasks, edit results, and export output.
- **Keyword boosting** menu: Register keywords for words you want to boost in recognition probability, and manage registered keywords.
- **Forbidden keyword filtering** menu: Register keywords you do not want to display in recognition results and manage registered keywords.
- **Settings** menu: View domain information.

              Note

              

Some features may not be displayed depending on the domain type.

## Launch the Builder

To run the Builder:

              Note

              

You must create a domain before using the Builder. For more information, see [Create domain](/docs/en/clovaspeech-domain#%EB%8F%84%EB%A9%94%EC%9D%B8%EC%83%9D%EC%84%B1).

1. In the NAVER Cloud Platform console, navigate to **Menu** > **All Services** > **AI Services** > **CLOVA Speech**.
2. Click the **Domain** menu for the **streaming recognition** type.
3. Click **[Launch Builder]** for the domain you want to use.

## Manage recognition tasks

Streaming recognition automatically saves the voice recognition results from the start of voice recognition until the stream ends to the customer's Object Storage. Once saved, the results can be edited using the recognition task management feature. From the **Task list** menu in the Builder, you can monitor the progress of recognized tasks. You can also edit recognition results using the result editor and export them in the desired format.

              Note

              

- Sentence segmentation of recognition results is determined by the End Point Detection (EPD) settings.
- If only punctuation-based segmentation (`usePeriodEpd`) is used, recognition results may not be split into sentences for languages such as English and Japanese, where punctuation may not be generated. Instead, the results may be saved as one long sentence, making them difficult to edit in the recognition result editor.
- In this case, when requesting streaming recognition, also configure segmentation based on silence intervals (`gapThreshold`) or maximum utterance length (`durationThreshold`) in the `semanticEpd` field under Config so that sentences are split at appropriate points.
- For detailed configuration instructions, see the [CLOVA Speech real-time streaming API guide](https://api.ncloud-docs.com/docs/en/ai-application-service-clovaspeech-grpc).

### Task list interface

The **Task list** menu includes the following components: ![clovaspeech-builder_list2_ko](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/clovaspeech-builder_list2_en.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D)

| Component | Description |
| --- | --- |
| ① Menu name | Current menu name |
| ② Task management features | Delete, export |
| ③ Search bar | Search tasks by task ID or result file location |
| ④ Task list | Show recognition tasks currently being viewed |

### View recognition task list

To view details about recognition tasks registered in the Builder:

1. In the domain's builder, click the **Task list** menu.
2. When the task list appears, review the recognition task details.
  - **Task ID**: Name of the media file used for recognition.
  - **Language**: Language used for the recognition task.
  - **Task status**: Current status of the task, displayed as one of the following:

| Task status | Description |
| --- | --- |
| **Waiting** | Task is waiting to be processed. - This occurs when all servers are busy. When a server becomes available, the status changes to **In progress**. - **[Cancel recognition task]**: Cancel the task. |
| **In progress** | Task is currently being processed. |
| **Canceled** | Task has been successfully canceled. |
| **Canceling** | Task is being canceled. |
| **Failed** | Task failed. - ![i-clovaspeech-more](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/i-clovaspeech-more.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D): Click to view the reason. |
| **Completed** | Task is complete. |
  - **Result file location**: Object Storage path where the result file is saved.
  - Click ![i-clovaspeech-window](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/i-clovaspeech-window.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D) to open the Object Storage console interface.
  - **Start date (UTC+09:00)**: Date and time when the task started.
  - **End date (UTC+09:00)**: Date and time when the task ended.
  - **Edit recognition result**: Click **[Edit recognition result]** to open the result editor (see [Use the result editor](/docs/en/clovaspeech-builder-streaming#%EC%9D%B8%EC%8B%9D%EA%B2%B0%EA%B3%BC%EC%88%98%EC%A0%95%EC%97%90%EB%94%94%ED%84%B0%EC%82%AC%EC%9A%A9)).

### Use the result editor

After a recognition task is completed, you can open the result editor to view the media file and recognized text together. You can also edit the recognition results and export them in the desired format.

#### Result editing interface

Running the result editor opens the result editing interface. Here is an overview of its components:

![clovaspeech-long-demo_ko](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/clovaspeech-long-demo_en.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D)

| Component | Description |
| --- | --- |
| ① Export | Exports the edited results. |
| ② Input file | - Plays or pauses the input file. - Displays the input file and recognized text information. |
| ③ Filter | Filters recognition results by speaker or confidence. |
| ④ Voice recognition results | - Displays recognized text in a timeline format. - Allows editing of detected speakers and text. |
| ⑤ Event detection results (not provided) | - Displays detected events (clapping, laughter, music) in a timeline format. - Allows editing of detected events. |

#### Edit and export recognition results

You can edit recognition results and export them in the desired format using the result editor.

              Note

              

You can export multiple result files at once using [Export recognition results](/docs/en/clovaspeech-builder-streaming#%EC%9D%B8%EC%8B%9D%EA%B2%B0%EA%B3%BC%EB%82%B4%EB%B3%B4%EB%82%B4%EA%B8%B0).

1. In the domain's builder, click the **Task list** menu.
2. Click **[Edit recognition result]** for a completed task in the task list.
3. In the result editing interface, review the recognition results.
  - When playing the media file, the corresponding text in the timeline is highlighted.
  - **[Speaker]**: Filter recognized text by speaker.
  - **[Confidence in recognition results]**: Filter recognized text by confidence scores.
4. Edit the recognition results if needed.
  - Edit speaker: Click the dropdown menu and select a speaker.
    - ![i-clovaspeech-speakerdelete](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/i-clovaspeech-speakerdelete.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D): Delete a speaker.
    - ![i-clovaspeech-speakeredit](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/i-clovaspeech-speakeredit.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D): Edit a speaker's name.
    - **[Add speaker]**: Add a new speaker.
  - Edit text: Click the marked row ![i-clovaspeech-resultedit](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/i-clovaspeech-resultedit.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D) to edit text, then click ![i-clovaspeech-resultedit2](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/i-clovaspeech-resultedit2.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D) to save.
    - To cancel edits, click ![i-clovaspeech-editcancel](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/i-clovaspeech-editcancel.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D).
    - Edited content is highlighted in green.
5. To export recognition results, click **[Export]**, enter settings information, and click **[OK]**.
  - **File name**: Enter a name for the output file.
  - **File format**: Click on the dropdown menu and select the file format you want to export the file as (select from `json`, `smi`, `srt`, `txt`, `csv`, and `xls`).
  - **Push timeline back**: Push the timeline backward by a specified amount.
  - **Export method**: Select **Object Storage** or **Download**.
    - For **Object Storage**, click the **file path** to select the save location.
    - For **Download**, the file is saved to your local PC.

### Export recognition results

You can export the result files of multiple tasks at once.

              Note

              

Only tasks with the **Task status** set to **Completed** can be exported.

1. In the domain's builder, click the **Task list** menu.
2. Select the tasks you want to export.
  - Multiple tasks can be selected at once.
3. Click **[Export]**.
4. When the **Export** popup appears, check the export settings and click **[OK]**.
  - ![i-clovaspeech-edit](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/i-clovaspeech-edit.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D): Click to edit the result file name.
  - ![i-clovaspeech-delete](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/i-clovaspeech-delete.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D): Click to delete a task from the export list.
  - **File format**: Click on the dropdown menu and select the file format you want to export the file as (select from `json`, `smi`, `srt`, `txt`, `csv`, and `xls`).
  - **Export method**: Select **Object Storage** or **Download**.
    - For **Object Storage**, click the **result file path** to select the save location.
    - For **Download**, the file is saved to your local PC.

### Delete recognition tasks

To delete registered recognition tasks:

1. In the domain's builder, click the **Task list** menu.
2. Select the task(s) you want to delete.
  - Multiple tasks can be selected at once.
3. Click **[Delete]**.
4. When the **Delete task** popup appears, click **[Delete]**.

## Keyword boosting

Keyword boosting allows you to increase recognition accuracy for specific words. In the **Keyword boosting** menu, you can register and manage keywords.

### Keyword boosting interface

The **Keyword boosting** menu includes the following components: ![clovaspeech-builder_keyword_ko](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/clovaspeech-builder_keyword_en.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D)

| Component | Description |
| --- | --- |
| ① Menu name | Current menu name |
| ② Keyword management features | Upload keyword files, download and delete registered keywords |
| ③ Search bar | Search keywords |
| ④ Keyword list | List of keywords being viewed |

### Add keywords

To add keywords you want to boost:

              Note

              

- You can add up to 1,000 words, and Korean and English are supported.
- It is recommended to register no more than 500 words. Registering more than 500 words may degrade performance.
- Higher weight values increase recognition of similar words, which may affect accuracy.

You can add keywords using either method below:

- [Upload a keyword file](/docs/en/clovaspeech-builder-streaming#%ED%82%A4%EC%9B%8C%EB%93%9C%ED%8C%8C%EC%9D%BC%EC%97%85%EB%A1%9C%EB%93%9C): Upload an Excel file containing keywords to add multiple keywords at once.
- [Add keywords individually](/docs/en/clovaspeech-builder-streaming#%ED%82%A4%EC%9B%8C%EB%93%9C%EA%B0%9C%EB%B3%84%EC%B6%94%EA%B0%80): Enter keywords directly in the Builder.

#### Upload keyword file

To upload an Excel file and register multiple keywords at once:

1. Prepare an Excel file containing the keywords and weight values.
  - Weight values must be integers between 1 and 5.
  - In step 4, click **Upload template** to view the keyword file template.
2. In the domain's Builder, click the **Keyword boosting** menu.
3. Click **[Upload]**.
4. When the **Upload** popup appears, **drag a file into the window or click here**. Drag and drop the keyword file into the window, or click on the window to select the keyword file.
5. Click **[OK]**.
  - Overwrite: Enable the checkbox to delete all existing keywords and register only the new keywords.

              Note

              

If the file contains keywords that have already been registered, the upload will fail. Remove duplicate keywords or enable overwrite when uploading.

#### Add keywords individually

To add keywords directly in the Builder:

1. In the domain's Builder, click the **Keyword boosting** menu.
2. **Enter the keyword you want to add.** Click on the input field and type the keyword.
3. Select a **weight** value from the dropdown menu.
4. Click **[Add]**.

### Edit keywords

To edit a registered keyword:

1. In the domain's Builder, click the **Keyword boosting** menu.
2. In the keyword list, click ![i-clovaspeech-edit](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/i-clovaspeech-edit.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D) for the keyword you want to edit.
3. Click the keyword input field, edit the keyword, and then click ![i-clovaspeech-keywordeditcheck](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/i-clovaspeech-keywordeditcheck.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D).
  - To cancel editing, click ![i-clovaspeech-keywordeditcancel](https://cdn.document360.io/6998976f-9d95-4df8-b847-d375892b92c2/Images/Documentation/i-clovaspeech-keywordeditcancel.png?sv=2026-02-06&spr=https&st=2026-11-14T05%3A05%3A04Z&se=2026-11-14T06%3A05%3A04Z&sr=c&sp=r&sig=r154vrENOvMgUKgL7E2kuP5Hin%2FIs1qv7oEMNgieuVQ%3D).
  - To edit the **weight**, select a new value from the dropdown menu.

### Download keywords

To download registered keywords:

1. In the domain's Builder, click the **Keyword boosting** menu.
2. In the keyword list, select the checkboxes for the keywords you want to download.
  - Multiple keywords can be selected at once.
3. Click **[Download]**.
  - An Excel file containing the keywords and weight information will be downloaded.

### Delete keywords

To delete registered keywords:

1. In the domain's Builder, click the **Keyword boosting** menu.
2. In the keyword list, select the checkboxes for the keywords you want to delete.
  - Multiple keywords can be selected at once.
  - You may also click the **[Delete]** button of the keyword to immediately delete the keyword.
3. Click **[Delete keywords]**.
4. When the notification popup appears, click **[OK]**.

## Check API call information and domain information

In the **Settings** menu, you can check the integration information required for API calls and the information of the domain connected to the Builder.

### Check API call information

To check the integration information required for API calls:

              Note

              

You can call the API to transfer audio files for recognition and receive recognition results. For more information about calling the API, see [CLOVA Speech API guide](https://api.ncloud-docs.com/docs/en/ai-application-service-clovaspeech).

1. In the domain's Builder, click the **Settings** menu.
2. Click the **[Integration information]** tab menu.
3. Check the domain's **Secret Key** and **CLOVA Speech Invoke URL**.
  - **[Create]**: Click to create or regenerate the Secret Key.
  - **[Copy]**: Click to copy the information to the clipboard.

### Check domain information

To check the information of the domain connected to the Builder:

1. In the domain's Builder, click the **Settings** menu.
2. Click the **[Domain information]** tab menu.
3. Check the domain information connected to the Builder.
  - **Domain information**
    - **Domain name**: Name of the domain.
    - **Domain code**: Code of the domain.
    - **Type**: Pricing plan applied to the domain.
  - **Storage settings**
    - **Result file storage path**: Object Storage path for saving recognition result files.
    - **Input file storage path**: Object Storage path for selecting input files.
    - **[Go to Object Storage]**: Click to move to the Object Storage console interface.