Transcribe an audio clip
Turns a short recording into text. Accepts what browsers and phones produce (webm/opus, mp4/m4a, ogg, wav, mp3, flac) up to 25 MB; no conversion to WAV is needed. The language is detected when not given.
Операция для поискового ключа
Turns a short recording into text. Accepts what browsers and phones produce (webm/opus, mp4/m4a, ogg, wav, mp3, flac) up to 25 MB; no conversion to WAV is needed. The language is detected when not given.
Authorization
api_key_header Every request carries an organization API key. A key has one of two scopes. A full key reaches every operation in this document and belongs on your server. A search key is the one to ship in a browser widget or a storefront page: it reaches only the operations marked x-nova-key-scope: search — searching, federated search, recommendations, event ingestion, and the visitor-facing AI operations (semantic and image search, voice transcription and voice search, assistant chat, and the visitor's own conversation). It cannot write documents or read or change configuration; any other operation answers 403. AI operations are paid in credits from the organization's wallet whichever key calls them (402 when the balance runs out), and a search key needs X-NOVA-SESSION-ID on them: the session is what a conversation belongs to, and what the per-session allowance (429) is counted against. A key of either scope may additionally carry restrictions set in the console: an allowlist of collections (403 elsewhere), a forced filter_by per collection that is ANDed into every search (document-level access control), an allowlist of fields (include_fields is limited to it and a request naming any other field in query_by, facet_by, sort_by, filter_by or highlight_fields answers 400), an IP/CIDR allowlist and an Origin/Referer allowlist (403), and a per-key rate limit (429 with Retry-After).
In: header
Request Body
multipart/form-data
TypeScript Definitions
Use the request body type in TypeScript.
Response Body
application/json
application/json
application/json
application/json
application/json
application/json
curl -X POST "https://example.com/voice/transcriptions" \ -F file="string"{ "text": "string", "language": "string", "duration_ms": 0, "segments": [ { "start_ms": 0, "end_ms": 0, "text": "string" } ], "model": "string"}Pre-search prompts GET
What to show before the visitor types (PRESEARCH surface): the session's or user's recent searches, contextual continuations of the last query (from the query graph), and what is trending on the collection. Sections are omitted when empty. Report a chosen item as a `suggestion_select` event with `query_id` = `presearch_id`.
Search a collection by voice POST
Transcribes the recording and runs a search with the text as `q`. Pass any search parameters (for example `query_by`, `filter_by`, `nl_query`) as a JSON object in the `params` field. The transcript is returned in `request_params.voice_query.transcribed_query`.