Introduction
Qwen-Audio 3.1 TTS Plus turns prepared writing into narration using four multilingual system voices from Alibaba's Qwen team. Its flagship positioning centers on fidelity for audiobooks, brand recordings, film dubbing and character performance.
Put the passage in text and the narrator direction in instructions, then submit the task and poll for completion. A request accepts up to 10,000 characters, with MP3 at 24,000 Hz as the default export.
Key features & highlights
- Choose among Long An Huan, Long An Lingxin, Long An Fengyue and Xun Anchuan.
- Guide a narrator through emotion, persona, tone and pacing without speaking the directions.
- Enable SSML when a passage needs markup for pronunciation, pauses or emphasis.
- Export narration as MP3, WAV, raw PCM or Opus at a supported sample rate.
Request parameters
| Parameter | Required | Description |
|---|---|---|
text | Yes | 3.1 TTS Plus script: required text, up to 10,000 characters, with no default script; its length determines the charge per 1,000 characters. at least 1 characters · at most 10000 characters |
voice_id | No | 3.1 TTS Plus casting: choose one of 4 multilingual system voices belonging to this model; other-model IDs are rejected, no default is specified in the supplied facts, and select… |
instructions | No | 3.1 TTS Plus direction: free-style emotion, tone, persona, pace or dialect notes that are not spoken or billed; no length limit or default direction is specified in the supplied… at most 1000 characters |
language | No | 3.1 TTS Plus language hint: auto by default, or zh, en, ja, ko, fr, de, pt, it, vi or id; this setting has no price effect. |
speed | No | 3.1 TTS Plus pace control: 0.5–2, default 1, to slow down or speed up speech without altering the charge. |
pitch | No | 3.1 TTS Plus pitch adjustment: 0.5–2 with default 1 changes vocal pitch and adds no cost. |
volume | No | 3.1 TTS Plus loudness setting: 0–100, default 50, changes output volume without a billing change. |
output_format | No | 3.1 TTS Plus encoding: mp3 by default, or wav, pcm (raw) and opus; the selected format does not change pricing. |
sample_rate | No | 3.1 TTS Plus sample rate: 8000, 12000, 16000, 22050, 24000 (default), 44100 or 48000 Hz; changing the rate leaves price unchanged. |
bitrate | No | 3.1 TTS Plus bitrate control applies to Opus and has no price effect; its numeric range and default are not specified in the supplied facts. |
enable_ssml | No | 3.1 TTS Plus markup switch: enable it to interpret text as SSML for pauses, pronunciation and emphasis; no default is specified in the supplied facts, and the switch adds no fee… Default: |
seed | No | 3.1 TTS Plus comparison seed: use the same random source while changing one setting, without expecting identical audio; no numeric range or default is specified in the supplied… |
Pricing
$0.029 / 1,000 characters
Qwen-Audio 3.1 TTS Plus billing is per 1,000 characters of text; instructions are not billed, and failed requests are not charged.
Use cases
- Audiobook chapters: Develop a chapter reading with an unhurried narrator and a consistent choice of preset across requests.
- Brand introductions: Try a smooth welcome for a travel brand, then refine its confidence and warmth in the direction field.
- Dubbing and character scenes: Prepare dialogue for a film or fictional character and audition the emotional delivery before editing.
Prompt guide & pro tips
- Start with the opening paragraph to judge the narrator before a full chapter. Example instruction: "Read as a patient storyteller, warm and slightly mysterious."
- Give brand recordings a clear speaking role. Example instruction: "Deliver a polished cruise welcome with quiet confidence."
- Describe a scene's emotional direction in a short note. Example instruction: "Keep the character thoughtful, with restrained excitement."
- Hold the seed steady while comparing one delivery change; audio may still vary. Example instruction: "Use the same calm tone with a slower ending."
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "alibaba/qwen-audio-3.1-tts-plus/text-to-speech",
"input": {
"text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
"language": "auto",
"voice_id": "longanhuan_v3.1",
"sample_rate": 24000,
"output_format": "mp3"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.








