Whisper Transcription

Audio transcription via OpenAI Whisper API.

Overview

Artemis proxies audio transcription requests to OpenAI's Whisper API, providing the same usage tracking and key management as LLM requests.

Endpoint: POST /v1/audio/transcriptions

Usage

Python

from openai import OpenAI

client = OpenAI(
    api_key="your-artemis-key",
    base_url="https://artemis.meetrhea.com/v1"
)

with open("audio.mp3", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="whisper-1",
        file=audio_file
    )

print(transcript.text)

curl

curl https://artemis.meetrhea.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $ARTEMIS_KEY" \
  -F file="@audio.mp3" \
  -F model="whisper-1"

Request Parameters

Parameter	Type	Required	Description
file	file	Yes	Audio file to transcribe
model	string	Yes	Model to use (whisper-1)
language	string	No	ISO-639-1 language code
prompt	string	No	Guide the model's style
response_format	string	No	json, text, srt, vtt, verbose_json
temperature	float	No	Sampling temperature (0-1)

Supported Formats

Audio files must be in one of these formats:

• mp3
• mp4
• mpeg
• mpga
• m4a
• wav
• webm

Maximum file size: 25 MB

Response

JSON (default)

{
  "text": "Hello, this is a transcription of the audio file."
}

Verbose JSON

{
  "task": "transcribe",
  "language": "english",
  "duration": 5.5,
  "text": "Hello, this is a transcription.",
  "segments": [
    {
      "id": 0,
      "start": 0.0,
      "end": 2.5,
      "text": "Hello, this is"
    }
  ]
}

SRT/VTT

Subtitle formats for video use.

Usage Tracking

Whisper requests are logged with:

• Audio duration (seconds)
• Cost (based on duration pricing)
• Provider key used

Pricing

OpenAI Whisper pricing: $0.006 per minute of audio.

Provider Key

Whisper uses OpenAI provider keys. Ensure you have an OpenAI key configured in your group's provider settings.

Error Handling

{
  "error": {
    "message": "File too large. Maximum size is 25MB.",
    "type": "invalid_request_error",
    "code": "file_too_large"
  }
}

Common Errors

Error	Cause
file_too_large	Audio file exceeds 25MB
invalid_file_format	Unsupported audio format
no_provider_key	No OpenAI key configured
provider_error	OpenAI API error

Integration with Speaches

For local Whisper transcription without OpenAI, use Speaches service instead.