Audio Transcription
Transcribe audio and video files to text with segment-level timestamps using Whisper.
The lt-transcription pipeline converts audio and video files to text using OpenAI Whisper. It returns a full transcript along with segment-level timestamps, detected language, and total duration.
250 credits per file · ~3 minutes
Accepted Files
| Type | MIME types |
|---|---|
| Audio | audio/* (MP3, WAV, M4A, OGG, FLAC, …) |
| Video | video/* (MP4, MOV, MKV, …) |
One file per run. Maximum file size: 25 MB (Whisper API limit).
Context Parameters
| Parameter | Required | Description |
|---|---|---|
language | No | ISO 639-1 language code of the spoken language (e.g. de, fr, es). If omitted, Whisper auto-detects the language. |
Providing the language code when you know it improves accuracy and reduces processing time.
Output
{
"pipelineSlug": "lt-transcription",
"output": {
"text": "Hello, this is a sample transcript of the audio file.",
"language": "English",
"languageCode": "en",
"duration": 120.5,
"segments": [
{
"start": 0.0,
"end": 2.8,
"text": "Hello, this is a sample"
},
{
"start": 2.8,
"end": 5.1,
"text": "transcript of the audio file."
}
]
},
"rawText": "Hello, this is a sample transcript of the audio file."
}Output Fields
| Field | Type | Description |
|---|---|---|
text | string | Full transcript as a single string |
language | string | Detected language name (e.g. "English") |
languageCode | string | ISO 639-1 code (e.g. "en") |
duration | number | Total audio duration in seconds |
segments | array | Segment-level breakdown with start, end, and text |
rawText | string | Alias of text for uniform access across pipeline types |
API Example
POST /v2/lt-pipelines/project/{projectId}/run{
"pipelineSlug": "lt-transcription",
"fileIds": ["file_abc123"],
"contextData": {
"language": "de"
}
}Response:
{
"runIds": ["ltrun_xyz789"]
}Retrieve the result once the run completes:
GET /v2/lt-pipelines/runs/ltrun_xyz789How is this guide?
LT Pipelines
Overview of all 7 Language Technology pipelines for transcription, translation, OCR, language identification, and entity detection.
Text Translation
Translate text files into any target language using an LLM.