API Docs
API Docs
Multi-Speaker Text to Text
Convert multi-speaker conversational input into structured, speaker-attributed text.
Create Multi-Speaker Text to Text Request
/api/ms-ttt
This endpoint creates a multi-speaker text to text request where each speaker segment is processed independently while preserving speaker attribution.
The request is processed asynchronously. Once accepted, the API returns a unique log_id that can be used to fetch the translated, speaker-separated output.
Request Body
project_title (string, required)
A human-readable title to identify the multi-speaker text to text project.
Example: "My Project"
segments (array, required)
List of speaker segments containing original text and timing information.
Example: [
{
"original_speaker": "SPEAKER_00",
"original_text": "regardless of my",
"start_time": "00:00:00,070",
"end_time": "00:00:00,910"
}
]
segments[].original_speaker (string, required)
Identifier of the speaker for the segment (for example: SPEAKER_00, SPEAKER_01).
segments[].original_text (string, required)
Original text spoken by the speaker in this segment.
segments[].start_time (string, required)
Start timestamp of the segment in HH:MM:SS,ms format.
Example: "00:00:00,070"
segments[].end_time (string, required)
End timestamp of the segment in HH:MM:SS,ms format.
Example: "00:00:00,910"
segments[].speed (number | null, optional)
Optional speech speed metadata associated with the segment.
segments[].pitch (number | null, optional)
Optional pitch metadata associated with the segment.
output_language (string, required)
Target language for the translated speaker segments.
View example →Response
On successful submission, the API returns a unique log_id.
Use this log_id with the Fetch Multi-Speaker Text to Text By ID endpoint to retrieve the translated, speaker-attributed output.
{
"log_id": "695031597d5247d58c029e93"
}curl
curl --location 'https://api.narris.io/api/ms-ttt' \
--header 'Content-Type: application/json' \
--header 'x-api-key: YOUR_API_KEY' \
--data '{
"project_title": "My Project",
"segments": [
{
"original_speaker": "SPEAKER_00",
"speed": null,
"pitch": null,
"original_text": "regardless of my",
"start_time": "00:00:00,070",
"end_time": "00:00:00,910"
}
],
"input_language": "english",
"output_language": "hindi",
"model": "narris"
}'Fetch Multi-Speaker Text to Text List
/api/ms-ttt/logs
This endpoint allows you to fetch a paginated list of previously created multi-speaker text to text requests.
Each entry represents a multi-speaker processing job and includes its current status and creation timestamp.
Request Body
page (number, optional)
Page number for pagination.
Example: 1
limit (number, optional)
Number of records to return per page.
Example: 20
Response
On success, the API returns a paginated list of multi-speaker text to text logs.
Each log contains a unique _id which can be used with the Fetch Multi-Speaker Text to Text By ID endpoint to retrieve the speaker-attributed translated output.
{
"total": 10,
"page": 1,
"limit": 20,
"logs": [
{
"_id": "695031597d5247d58c029e93",
"project_title": "My Project",
"status": "finished",
"createdAt": "2025-12-27T19:19:53.378Z"
},
{
"_id": "694459d4d408648d0d9efe0c",
"project_title": "My Project",
"status": "failed",
"createdAt": "2025-12-18T19:45:24.359Z"
}
]
}curl
curl --location 'https://api.narris.io/api/ms-ttt/logs?page=1&limit=20' \ --header 'Content-Type: application/json' \ --header 'x-api-key: YOUR_API_KEY'
Fetch Multi-Speaker Text to Text By ID
/api/ms-ttt/{log_id}
This endpoint allows you to fetch the complete details of a multi-speaker text to text request using its unique log_id.
The response preserves speaker attribution and returns translated text for each speaker segment along with timing metadata.
Request Body
log_id (string, required)
Unique identifier of the multi-speaker text to text request returned during creation or from logs.
Example: "694b08eebca52cafa955756d"
Response
On success, the API returns detailed information about the multi-speaker text to text request.
Each segment includes both the original and translated text while preserving speaker labels and timestamps.
{
"_id": "694b08eebca52cafa955756d",
"project_title": "My Project",
"segments": [
{
"original_speaker": "SPEAKER_00",
"speed": null,
"pitch": null,
"original_text": "regardless of my",
"start_time": "00:00:00,070",
"end_time": "00:00:00,910",
"translated_text": "मेरी परवाह किए बिना"
}
],
"input_language": "english",
"output_language": "hindi",
"model": "narris",
"status": "finished",
"createdAt": "2025-12-23T21:26:06.579Z",
"updatedAt": "2025-12-23T21:26:21.750Z"
}curl
curl --location 'https://api.narris.io/api/ms-ttt/694b08eebca52cafa955756d' \ --header 'Content-Type: application/json' \ --header 'x-api-key: YOUR_API_KEY'
Notes for Developers
• Multi-speaker text to text requests are processed asynchronously. Always store the returned log_id to track processing status.
• Each request may contain multiple speaker segments, and the final output will preserve speaker boundaries and labels.
• Jobs may remain in pending or processing state depending on conversation length and system load.
• Use the Fetch Multi-Speaker Text to Text List endpoint to view all jobs and Fetch Multi-Speaker Text to Text By ID to retrieve the final structured output.