Qwen Audio 4 API & Playground

Examples

Explore prompt configurations

Cinematic product reveal

Natural character motion

Multi-shot story

README

Build with Qwen Audio 4

Production-ready text to speech with normalized inputs, predictable task states, and unified billing. Use the playground above to explore the model visually, then send the same structured payload through the unified API when you are ready to ship.

Fast integration

One endpoint and predictable task states.

Commercial use

Outputs are available for commercial projects.

API ready

Form values map directly to JSON fields.

Schema v1

Parameters

Unknown fields rejected

FieldTypeRequiredDefault / availability

prompt

Prompt

stringYes

A cinematic scene with natural motion, expressive lighting, and a clear visual story.

How it works

1
Configure your generation inputs
The unified task contract remains the same when switching between compatible models.
2
Submit a task through the API or playground
The unified task contract remains the same when switching between compatible models.
3
Poll the task or receive a webhook with the result
The unified task contract remains the same when switching between compatible models.

Pricing

ModelPrice

Qwen Audio 4$0.022 / request

Failed tasks are automatically refunded.

API

Use the same payload from the playground through the unified task endpoint.

curl -X POST /api/v1/tasks \
  -H "Authorization: Bearer $EVERYROUTER_API_KEY" \
  -H "Idempotency-Key: my-generation-001" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen-audio-4-54","input":{"prompt":"..."}}'