Audio transcription (Speech-to-Text) with Velqa.dev

Velqa offers audio transcription via whisper-large-v3 (multilingual, strong in French / Arabic / darija), on the OpenAI-compatible API https://api.velqa.dev/v1/audio/transcriptions. Ideal for transcribing meetings, voice notes or customer calls.

Pricing and access

Unlike chat and embedding models, audio is billed per minute rather than per token, from your Recharge Boost balance (prepaid credit) — it is not included in any Starter/Dev/Pro plan.

• Indicative price: ~0.10 MAD / minute
• Access: any account with a positive Boost balance
• Max duration per file: 10 minutes
• The exact billed price depends on the real (rounded) file duration, shown in the usage history of your dashboard.

If the Boost balance is insufficient to cover the maximum reserved duration, the request is rejected (HTTP 402) before it ever reaches the model.

Example with curl

curl https://api.velqa.dev/v1/audio/transcriptions \
  -H "Authorization: Bearer $VELQA_API_KEY" \
  -F file=@meeting.mp3 \
  -F model=whisper-large-v3

Example with Python

from openai import OpenAI

client = OpenAI(base_url="https://api.velqa.dev/v1", api_key="VELQA_API_KEY")
with open("meeting.mp3", "rb") as f:
    tr = client.audio.transcriptions.create(model="whisper-large-v3", file=f)
print(tr.text)

The response contains text, the transcribed text. The real cost (based on file duration) is debited from your Boost balance.