Skip to main content
POST
/
api
/
v2
/
audio
/
transcriptions
cURL
curl --request POST \
  --url https://api.deapi.ai/api/v2/audio/transcriptions \
  --header 'Accept: <accept>' \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form include_ts=true \
  --form model=WhisperLargeV3 \
  --form 'source_url=https://www.youtube.com/watch?v=jNQXAC9IVRw' \
  --form source_file='@example-file' \
  --form return_result_in_response=false \
  --form webhook_url=https://your-server.com/webhooks/deapi
{
  "data": {
    "request_id": "c08a339c-73e5-4d67-a4d5-231302fbff9a"
  }
}
Unified transcription endpoint that replaces the five v1 endpoints (vid2txt, aud2txt, videofile2txt, audiofile2txt, transcribe). Accepts URLs or multipart file uploads. Returns a request_id for status polling.
Source detection is automatic: pass a public video_url / audio_url, or upload a file via multipart form-data.
Prerequisite: Consult the Model Selection endpoint to identify a valid model slug and check supported languages.
OpenAI SDK users: This endpoint is also available via the OpenAI-compatible surface as POST /v1/audio/transcriptions at https://oai.deapi.ai/v1. Maximum file size per upload is 20 MB for audio and 50 MB for video, subject to a global 75 MB request body cap. See OpenAI Compatibility and Limits & Quotas.

Authorizations

​
Authorization
string
header
required

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

Headers

​
Accept
enum<string>
default:application/json
required
Available options:
application/json

Body

multipart/form-data

Transcription parameters. Provide exactly one of source_url or source_file.

​
include_ts
boolean
required

Should transcription include timestamps

​
model
string
required

The model to use for transcription. Available models can be retrieved via the GET /api/v1/client/models endpoint.

Example:

"WhisperLargeV3"

​
source_url
string

URL of video/audio to transcribe (YouTube, Twitter/X, Twitch, Kick, TikTok, Twitter Spaces). Mutually exclusive with source_file.

Example:

"https://www.youtube.com/watch?v=jNQXAC9IVRw"

​
source_file
file

Audio or video file to transcribe. Supported audio: aac, mpeg, ogg, wav, webm, flac (max 20 MB). Supported video: mp4, mpeg, quicktime, avi, wmv, ogg (max 50 MB). Total request body is capped at 75 MB. Mutually exclusive with source_url.

​
return_result_in_response
boolean | null
default:false

If true, the result will be returned directly in the response instead of only download url.

​
webhook_url
string<uri> | null

Optional HTTPS URL to receive webhook notifications for job status changes.

Maximum string length: 2048
Example:

"https://your-server.com/webhooks/deapi"

Response

ID of the inference request.

​
data
object

Information from success endpoint