Qwen3-TTS API — Multilingual Text to Speech

Qwen3-TTS uses asynchronous speech tasks. Send an inputs array of prompt/language objects, then poll the saved task ID.

Qwen3-TTS is a speech / audio model on KeyoAPI, a prepaid AI API gateway: call it at POST /v1/async/audio/speech, billed at $0.548 / 10K characters from the same balance that covers chat, vision, OCR and video models.

Listed price: $0.548 / 10K characters · Live catalog: Model Square · Static list: pricing list.

Overview

Qwen3-TTS is an asynchronous text-to-speech option on KeyoAPI. Submit text with your existing API key, save the returned task identifier, and retrieve the finished audio when processing completes. It shares the account wallet with speech recognition, chat and avatar tasks, but each capability has its own request fields and result rules.

POST /v1/async/audio/speech with model=Qwen3-TTS and an inputs array. Each object requires prompt and language (Chinese or English); send one to five items. Optional speaker names are case-sensitive: Vivian, Serena, Uncle_Fu, Dylan, Eric, Ryan, Aiden, Ono_Anna and Sohee. An optional instruction guides expression. This is not a generic voice field, and a style instruction does not guarantee gender, emotion or speaker identity. For older clients, the gateway converts a string or single-object input/inputs to an array. New clients should use the canonical array and an explicit language.

After submission, save id or task_id before doing other work. Query GET /v1/task/{id} with the same API key while status is processing. On completed, inspect the actual output. Download from url or output.file_url only if present. For batch requests, process each returned item rather than assuming one audio URL. Keep the complete response for support if the output shape is unexpected; do not automatically submit a replacement. Stop on failed or cancelled and preserve the error and request identifier for support. Do not use the plural video query path /v1/tasks/{id} for this endpoint.

Reference mode uses prompt_audio_url and its matching prompt_text inside an inputs item, not at the top level. Replace example URLs with real downloadable reference files and exact transcripts. This page does not define enrollment or reusable voice IDs. Confirm those workflows with support; do not invent reference_audio, speaker_id or voice fields from another model. The built-in speaker example below does not submit a reference sample or guarantee speaker reproduction.

For application integration, store the task ID with your own request record. A temporary query failure can be retried with that same ID. A submission timeout is ambiguous and should not trigger an automatic replacement speech task: the original may already be processing. Keep API keys on the server and record errors without authorization headers or raw private media.

Check the pricing page for the model's currently applicable rate and account group. Read the API endpoint reference for the asynchronous speech flow, the TTS API guide for the sync and async endpoint map, and the voice cloning API guide for the distinction between synthesis and cloning. If you need audio bytes in a single response, compare the separately documented synchronous models instead of changing the async task URL.

• Listed price: $0.548 / 10K characters
• Billing base: $1 of wallet balance = 500,000 quota units
• Gift credit: new users get $10, invites add $3 (spend-first on :free IDs)
• Endpoint: POST /v1/async/audio/speech with Bearer auth on https://www.keyoapi.xyz/v1

How to call it

curl https://www.keyoapi.xyz/v1/async/audio/speech \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"Qwen3-TTS","output_format":"mp3","inputs":[{"prompt":"Hello from KeyoAPI TTS.","language":"English","speaker":"Vivian"}]}'
# Save id/task_id, then GET /v1/task/{id} with the same key.

FAQ

Related models

Guide for Qwen3-TTS. Catalog: the pricing page · Rates: the full pricing list.