Skip to main content
POST
/
v1
/
audio
/
translations
Typescript
const client = new Dedalus();

const result = await client.audio.translations.create({ ...params });
{
  "language": "<string>",
  "duration": 123,
  "text": "<string>",
  "segments": [
    {
      "id": 123,
      "seek": 123,
      "start": 123,
      "end": 123,
      "text": "<string>",
      "tokens": [
        123
      ],
      "temperature": 123,
      "avg_logprob": 123,
      "compression_ratio": 123,
      "no_speech_prob": 123
    }
  ]
}

Overview

Translate audio files from any supported language to English text. Useful for international content localization and multilingual transcription. Note: OpenAI only endpoint.

Usage Examples

curl -X POST https://api.dedaluslabs.ai/v1/audio/translations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F file="@audio.mp3" \
  -F model="openai/whisper-1"

Authorizations

Authorization
string
header
required

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

Body

multipart/form-data
file
file
required
model
string
required
prompt
string | null
response_format
string | null
temperature
number | null

Response

Successful Response

Fields: # noqa: D415.

  • language (required): str
  • duration (required): float
  • text (required): str
  • segments (optional): list[TranscriptionSegment]
language
string
required

The language of the output translation (always english).

duration
number
required

The duration of the input audio.

text
string
required

The translated text.

segments
TranscriptionSegment · object[]

Segments of the translated text and their corresponding details.

Last modified on April 9, 2026