Get Batch Transcription By Client Item ID | SoferAi

Resolve a batch item’s client_item_id to the resulting transcription.

client_item_id values are unique only within a batch, so this lookup is scoped by batch_id.

The response is a standard TranscriptionInfo object. Its id field is the canonical transcription ID for the batch item.

Resolve a batch item's `client_item_id` to the resulting transcription. `client_item_id` values are unique only within a batch, so this lookup is scoped by `batch_id`. The response is a standard [TranscriptionInfo](/api-reference/transcribe/get-transcription-status) object. Its `id` field is the canonical transcription ID for the batch item.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Path parameters

batch_idUUIDRequired

The batch ID returned from Create Batch Transcription

Query parameters

client_item_idstringRequired

The caller-defined client_item_id to resolve within this batch.

Response

This endpoint returns an object.

idUUID

ID of the transcription

titlestring

Title of the transcription

created_atdatetime

When the transcription was created

primary_languageenum

The primary language of the audio content, which can be English (en), Hebrew (he), Yiddish (yi), or French (fr).

hebrew_word_formatlist of enums

Indicates how Hebrew words are transcribed in the response when the primary language is English.

Hebrew words are in Hebrew letters if “he” is specified.
Hebrew words are transliterated into English letters if “en” is specified.
If both “he” and “en” are specified, both versions are provided back-to-back for each Hebrew word. Transliterated Hebrew words are surrounded by <i> tags in the response text.

statusenum

Current status of the transcription

client_item_idstring

Caller-defined per-item identifier for batch items. This is null for single transcriptions and for batch items submitted without a client_item_id.

num_speakersinteger

Number of speakers in the audio. This can be null while auto-detection is pending or if no count was determined.

durationdouble

Duration of the audio in seconds. If None, it means the duration was not calculated yet.

modelstring

Model used for the transcription. V1 is the latest and most accurate model, especially for audio with longer stretches of Hebrew. V0 is suitable for audio with fewer Hebrew words.

Errors

401

Authentication Error

404

Batch Item Not Found

404

Batch Not Found

429

Rate Limit Error

1	from soferai import SoferAI
2	import uuid
3
4	client = SoferAI(
5	api_key="YOUR_TOKEN_HERE",
6	)
7
8	client.batch_transcribe.get_batch_transcription_by_client_item_id(
9	batch_id=uuid.UUID("a1b2c3d4-e5f6-7890-abcd-ef1234567890"),
10	client_item_id="shiur_1",
11	)

1	{
2	"id": "d5e9c84f-c2b2-4bf4-b4b0-7ffd7a9ffc32",
3	"title": "Shiur 1",
4	"created_at": "2024-01-15T09:30:00Z",
5	"primary_language": "en",
6	"hebrew_word_format": [
7	"en",
8	"he"
9	],
10	"status": "COMPLETED",
11	"client_item_id": "shiur_1",
12	"num_speakers": 1,
13	"duration": 1802.5,
14	"model": "v1"
15	}