Submit an asynchronous background text processing job
Queue an asynchronous background job for long documents, transcripts, or batch workflows that exceed HTTP request timeouts. ### Task Types (`task`) - `translate`: Asynchronously translates text to `target_language`. - `redact`: Asynchronously masks PII into standardized placeholders. - `summarize`: Asynchronously generates a summary (`short`, `detailed`, or `structured`). ### Processing Architecture - Work is queued to a dedicated Celery LLM worker pool at batch priority. - Celery worker auto-retries and absorbs model cold starts gracefully without holding HTTP connections open. - Provenance tracking via optional `source_audio_id` links text jobs to original audio transcription records.
api/v1/text/{task}/jobsAuthorization
AuthorizationRequiredBearer <token>
In: header
Request Body
application/jsonRequireddomainAny properties in TextDomain
Optional industry vertical domain for vocabulary specialization. Defaults to 'general conversation' if omitted.
languageRequiredLanguage
Source language of the input text. Must be one of the 19 supported African or global languages.
"Afrikaans" | "Amharic" | "Arabic" | "English" | "French" | "German" | "Hausa" | "Igbo" | "Isixhosa" | "Italian" | "Kinyarwanda" | "Sesotho" | "Setswana" | "Shona" | "Spanish" | "Swahili" | "Twi" | "Yoruba" | "Zulu"source_audio_idSource Audio Id
Optional ID of the originating audio transcription record to preserve end-to-end data lineage.
styleSummaryStyle
Summary format. Applicable only when submitting a summarization job.
"short"Value in: "short" | "detailed" | "structured"target_languageAny properties in Language
Target language for translation. Required when submitting a translation job.
textRequiredText
Full text or transcript to process asynchronously.
1Path Parameters
taskRequiredTextTask
Text processing task type to execute asynchronously ('translate', 'redact', 'summarize')
"translate" | "redact" | "summarize"Job accepted and queued for background processing.