whisper-1 API

Speech-to-text (OpenAI Whisper). Billed by audio duration: 1 minute = 1000 tokens. Sync POST /v1/audio/transcriptions.

Try online · Get an API key · Read the docs

Capabilities

Model: Audio
API model: whisper-1
Endpoints: audio-transcription
Parameters: duration, format, voice, language

Current pricing

Pricing varies by request parameters.

Quick start

curl https://api.seedance.nz/v1/audio/transcriptions \
  -H "Authorization: Bearer $SEEDANCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"whisper-1","prompt":"A clear description of the scene"}'

from openai import OpenAI
client = OpenAI(base_url="https://api.seedance.nz/v1", api_key="$SEEDANCE_API_KEY")
  result = client.audio.speech.create(model="whisper-1", input="A clear description of the scene")

const client = new OpenAI({ baseURL: 'https://api.seedance.nz/v1', apiKey: process.env.SEEDANCE_API_KEY });
  const result = await client.audio.speech.create({ model: 'whisper-1', input: 'A clear description of the scene' });

Frequently asked questions

How do I call this model?

Create an API key, choose the model name below, and send a request to the documented OpenAI-compatible endpoint. Final billing follows the current price and usage parameters.