Introduction
Qwen-Audio 3.0 TTS Flash is Alibaba's option for assistants, live dialogue and customer-service speech with low first-packet latency as its positioning. It uses the same 597-preset catalog as 3.0 Plus and has the lowest price in the 3.0 line.
Send a prepared response and a matching Flash preset, then poll the submitted task until synthesis finishes. First-packet positioning does not establish a completion deadline for this asynchronous API, so measure the full interaction in your call flow.
Key features & highlights
- Reuse the 3.0 catalog's voice choices while selecting the matching Flash voice ID.
- Set an efficient assistant tone through instructions that add no billed characters.
- Keep service prompts within the 10,000-character request limit.
- Choose MP3, WAV, raw PCM or Opus to match your audio pipeline.
Request parameters
| Parameter | Required | Description |
|---|---|---|
text | Yes | 3.0 TTS Flash 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 Flash 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 n… |
instructions | No | 3.0 TTS Flash 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 supplie… at most 1000 characters |
language | No | 3.0 TTS Flash 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 Flash pace control: 0.5–2, default 1, to slow down or speed up speech without altering the charge. |
pitch | No | 3.0 TTS Flash pitch adjustment: 0.5–2 with default 1 changes vocal pitch and adds no cost. |
volume | No | 3.0 TTS Flash loudness setting: 0–100, default 50, changes output volume without a billing change. |
output_format | No | 3.0 TTS Flash encoding: mp3 by default, or wav, pcm (raw) and opus; the selected format does not change pricing. |
sample_rate | No | 3.0 TTS Flash sample rate: 8000, 12000, 16000, 22050, 24000 (default), 44100 or 48000 Hz; changing the rate leaves price unchanged. |
bitrate | No | 3.0 TTS Flash 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 Flash 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 fe… Default: |
seed | No | 3.0 TTS Flash 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
$0.014 / 1,000 characters
Qwen-Audio 3.0 TTS Flash charges per 1,000 characters in text, excluding instructions from billing and charging nothing for failed requests.
Use cases
- Booking assistants: Speak a reservation confirmation and its follow-up question with a friendly, efficient delivery.
- Order status hotlines: Turn a prepared shipping update into a clear recording for a customer-service call flow.
- Live dialogue responses: Audition short assistant turns and measure completion time within your own application.
Prompt guide & pro tips
- Use a direct service manner for transactional prompts. Example instruction: "Speak as a friendly, efficient booking assistant."
- Make an order update easy to follow through a clear delivery note. Example instruction: "Read the shipping update calmly and clearly."
- Audition a measured pace before increasing the speed setting. Example instruction: "Keep a brisk rhythm while making every detail clear."
- Test a single reply before generating an entire call flow. Example instruction: "Ask the follow-up question with a helpful, neutral tone."
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${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: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "alibaba/qwen-audio-3.0-tts-flash/text-to-speech",
"input": {
"text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
"language": "auto",
"voice_id": "qwen-audio-3.0-tts-flash-loonglunawang",
"sample_rate": 24000,
"output_format": "mp3"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.








