Introduction
Qwen-Audio 3.0 TTS Plus gives social and companion apps an expressive preset cast from Alibaba's Qwen team. The 597 voices include 589 Chinese presets and eight English presets for character dialogue and conversational recordings.
Keep the dialogue in text, then describe the personality and feeling in instructions. Synthesis runs asynchronously: submit a request, poll its task and review the resulting speech before using it in your app.
Key features & highlights
- Audition eight English voices alongside a catalog of 589 Chinese presets.
- Describe a companion's mood or a coach's energy using free-style performance notes.
- Adjust speed from 0.5 to 2 and pitch from 0.5 to 2 for a chosen character.
- Add SSML pronunciation, emphasis and pause markup when dialogue needs closer control.
Request parameters
| Parameter | Required | Description |
|---|---|---|
text | Yes | 3.0 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 | 3.0 TTS Plus casting: choose one of 597 preset voices belonging to this model; other-model IDs are rejected, no default is specified in the supplied facts, and selection does no… |
instructions | No | 3.0 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 | 3.0 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 | 3.0 TTS Plus pace control: 0.5–2, default 1, to slow down or speed up speech without altering the charge. |
pitch | No | 3.0 TTS Plus pitch adjustment: 0.5–2 with default 1 changes vocal pitch and adds no cost. |
volume | No | 3.0 TTS Plus loudness setting: 0–100, default 50, changes output volume without a billing change. |
output_format | No | 3.0 TTS Plus encoding: mp3 by default, or wav, pcm (raw) and opus; the selected format does not change pricing. |
sample_rate | No | 3.0 TTS Plus sample rate: 8000, 12000, 16000, 22050, 24000 (default), 44100 or 48000 Hz; changing the rate leaves price unchanged. |
bitrate | No | 3.0 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 | 3.0 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 | 3.0 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
$0.019 / 1,000 characters
For Qwen-Audio 3.0 TTS Plus, charges use units of 1,000 text characters; performance instructions carry no charge and failed requests incur none.
Use cases
- Companion conversations: Write a supportive reply and audition a soft, playful performance for a fictional companion.
- Social app characters: Give each character a chosen preset and a short persona direction for their spoken posts.
- Coaching encouragement: Pair a workout script with upbeat guidance that carries encouragement through the final repetition.
Prompt guide & pro tips
- Define the character's manner before tuning individual sliders. Example instruction: "Sound friendly, curious and a little playful."
- Use one emotional intention per audition to make comparisons easier. Example instruction: "Offer reassurance with gentle, steady confidence."
- Keep coaching direction separate from the words of encouragement. Example instruction: "Speak like an upbeat gym coach cheering the final set."
- Compare a short reply in several presets before choosing a cast member. Example instruction: "Read with relaxed warmth, as if catching up by phone."
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${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: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "alibaba/qwen-audio-3.0-tts-plus/text-to-speech",
"input": {
"text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
"language": "auto",
"voice_id": "qwen-audio-3.0-tts-plus-loonglunawang",
"sample_rate": 24000,
"output_format": "mp3"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.








