---
title: "Create a job for Salad Transcription Lite API"
method: POST
path: "/organizations/{organization_name}/inference-endpoints/transcription-lite/jobs"
tags: ["inference_endpoints"]
---

# Create a job for Salad Transcription Lite API

`POST /organizations/{organization_name}/inference-endpoints/transcription-lite/jobs`

## Request

- Base URL: `https://api.salad.com/api/public`
- URL: `https://api.salad.com/api/public/organizations/{organization_name}/inference-endpoints/transcription-lite/jobs`
- Auth: API key in header `Salad-Api-Key`
- TypeScript: <https://skmtc.dev/salad/apis/saladcloud-api/docs/organizations/:organization_name/inference-endpoints/transcription-lite/jobs/post.ts> (a function with typed inputs; its response is checked against the schema)

Creates a job for Salad Transcription Lite API

## Request body

- CreateSaladCloudTranscriptionLiteAPIJob: Create a job for Salad Transcription Lite API
  - `input` SaladCloudTranscriptionLiteAPIInput, required
    - `url` string, uri, required: URL of the audio file to process. Must be a downloadable link.
    - `language_code` string: Language code for the transcription. Defaults to 'en' (English).
    - `return_as_file` boolean: Whether to return the result as a file.
    - `sentence_level_timestamps` boolean: Return sentence-level timestamps in the transcription.
    - `word_level_timestamps` boolean: Return word-level timestamps in the transcription.
    - `diarization` boolean: Perform speaker diarization (separate speakers in multi-speaker audio).
    - `sentence_diarization` boolean: Perform sentence-level speaker diarization.
    - `srt` boolean: Generate an SRT file (SubRip Subtitle format).
    - `translate` string: Translate the transcription to English (set to 'to eng' to enable translation).
  - `metadata` object, nullable
  - `webhook` string, url, nullable

## Response `201`

Created

- SaladCloudTranscriptionLiteAPIJob: Job input schema for Salad Transcription Lite API
  - `id` string, uuid, required
  - `input` SaladCloudTranscriptionLiteAPIInput, required
    - `url` string, uri, required: URL of the audio file to process. Must be a downloadable link.
    - `language_code` string: Language code for the transcription. Defaults to 'en' (English).
    - `return_as_file` boolean: Whether to return the result as a file.
    - `sentence_level_timestamps` boolean: Return sentence-level timestamps in the transcription.
    - `word_level_timestamps` boolean: Return word-level timestamps in the transcription.
    - `diarization` boolean: Perform speaker diarization (separate speakers in multi-speaker audio).
    - `sentence_diarization` boolean: Perform sentence-level speaker diarization.
    - `srt` boolean: Generate an SRT file (SubRip Subtitle format).
    - `translate` string: Translate the transcription to English (set to 'to eng' to enable translation).
  - `inference_endpoint_name` string, required: The inference endpoint name
  - `metadata` object, nullable
  - `webhook` string, url, nullable
  - `status` 'pending' | 'running' | 'succeeded' | 'cancelled' | 'failed', required
  - `events` InferenceEndpointJobEvent[], required
    - `action` 'created' | 'started' | 'succeeded' | 'cancelled' | 'failed', required
    - `time` string, date-time, required
  - `organization_name` string, required: The organization name
  - `output` SaladCloudTranscriptionLiteAPIOutput
    - `sentence_level_timestamps` object[]: List of sentences with timestamps, speaker identification.
      - `text` string, required: Transcribed sentence.
      - `timestamp` number[]: Start and end times of the sentence in seconds.
      - `start` number, float, required: Start time of the sentence in seconds.
      - `end` number, float, required: End time of the sentence in seconds.
      - `speaker` string, required: Identified speaker label.
    - `word_segments` object[]: List of words with timestamps, confidence scores, and speaker identification.
      - `word` string, required: Transcribed word.
      - `start` number, float, required: Start time of the word in seconds.
      - `end` number, float, required: End time of the word in seconds.
      - `score` number, float, required: Confidence score for the transcribed word.
      - `speaker` string, required: Identified speaker label.
    - `srt_content` string: Generated SRT (SubRip Subtitle) content.
    - `text` string, required: Full transcribed text from the audio.
    - `duration` number, float, required: Duration of the audio file in hours.
    - `processing_time` number, float, required: Time taken to process the transcription in seconds.
  - `create_time` string, date-time, required
  - `update_time` string, date-time, required

## Other responses

- `400`: Bad Request
- `404`: Not Found
- `429`: Too Many Requests
- `default`: Unknown Error

---

[API](https://skmtc.dev/salad/apis/saladcloud-api.md) - [All operations](https://skmtc.dev/salad/apis/saladcloud-api/llms.txt) - [OpenAPI document](https://skmtc.dev/salad/apis/saladcloud-api/revisions/6ee34c3732f3?raw)