# Qwen-Audio 3.1 TTS Flash — Atlas Cloud API

> Alibaba's low-latency 3.1-generation text-to-speech model: rich system voices covering multiple foreign languages and Chinese dialects (Shanghainese, Cantonese, Northeastern, Sichuanese, and more), with free-style instruction control over emotion, tone, role, speed, and volume. Tuned for first-packet latency in real-time interaction.

This is the machine-readable API reference for **Qwen-Audio 3.1 TTS Flash** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `alibaba/qwen-audio-3.1-tts-flash/text-to-speech`
- **Built by**: Alibaba
- **Modality**: Audio
- **Model page**: https://www.atlascloud.ai/models/alibaba/qwen-audio-3.1-tts-flash/text-to-speech
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.002 per 1K characters
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_audio` with `model: "alibaba/qwen-audio-3.1-tts-flash/text-to-speech"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas models get alibaba/qwen-audio-3.1-tts-flash/text-to-speech --json
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateAudio` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `alibaba/qwen-audio-3.1-tts-flash/text-to-speech`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  Model name.
  - Default: `"alibaba/qwen-audio-3.1-tts-flash/text-to-speech"`

- **`text`** (`string`, _required_):
  Text to synthesize into speech audio. Tuned for low-latency interaction; supports multiple foreign languages and Chinese dialects, and free-style instruction control. Supports SSML and LaTeX input when enable_ssml is true.
  - Default: `"Welcome to Atlas Cloud — One API for All Media AI."`

- **`voice`** (`string`, _required_):
  System voice for qwen-audio-3.1-tts-flash (Singapore deployment). Lists the 70 Singapore-available system voices (4 multilingual/dialect + 15 premium English + 51 secondary-language). Premium-Chinese and other-Mandarin voices from the official list are Beijing-region only and are excluded. Secondary-language voices use the fully qualified id form qwen-audio-3.1-tts-flash-<name>_<lang>. The field also accepts any voice id outside this list and forwards it as-is. Dialect/language is selected at request time via the instruction field (e.g. 请讲上海话).
  - Default: `"longanhuan_v3.1"`
  - Options: "longanhuan_v3.1", "longanlingxin_v3.1", "longanfengyue_v3.1", "xunanchuan_v3.1", "Emily_v3.1", "Luna_v3.1", "Eric_v3.1", "Luca_v3.1", "Abby_v3.1", "Annie_v3.1", "Ava_v3.1", "Beth_v3.1", "Betty_v3.1", "Cally_v3.1", "Cindy_v3.1", "Donna_v3.1", "Andy_v3.1", "Brian_v3.1", "David_v3.1", "qwen-audio-3.1-tts-flash-zora_bg", "qwen-audio-3.1-tts-flash-linde_nl", "qwen-audio-3.1-tts-flash-hajnal_hu", "qwen-audio-3.1-tts-flash-senin_ro", "qwen-audio-3.1-tts-flash-birk_da", "qwen-audio-3.1-tts-flash-lipa_hr", "qwen-audio-3.1-tts-flash-avgi_el", "qwen-audio-3.1-tts-flash-jitrenka_cs", "qwen-audio-3.1-tts-flash-solglimt_nn", "qwen-audio-3.1-tts-flash-glimma_sv", "qwen-audio-3.1-tts-flash-svar_hi", "qwen-audio-3.1-tts-flash-iskra_sk", "qwen-audio-3.1-tts-flash-aava_fi", "qwen-audio-3.1-tts-flash-sahar_ur", "qwen-audio-3.1-tts-flash-jasna_sr", "qwen-audio-3.1-tts-flash-brisa_es_mx", "qwen-audio-3.1-tts-flash-ausra_lt", "qwen-audio-3.1-tts-flash-rasa_lv", "qwen-audio-3.1-tts-flash-deniz_tr", "qwen-audio-3.1-tts-flash-ava_fa", "qwen-audio-3.1-tts-flash-or_he", "qwen-audio-3.1-tts-flash-ayalguu_mn", "qwen-audio-3.1-tts-flash-zarja_sl", "qwen-audio-3.1-tts-flash-ishiq_az", "qwen-audio-3.1-tts-flash-zorza_pl", "qwen-audio-3.1-tts-flash-alba_ca", "qwen-audio-3.1-tts-flash-romduol_km", "qwen-audio-3.1-tts-flash-aurora_pt_br", "qwen-audio-3.1-tts-flash-dao_lo", "qwen-audio-3.1-tts-flash-tsiskari_ka", "qwen-audio-3.1-tts-flash-lente_af", "qwen-audio-3.1-tts-flash-kiran_ne", "qwen-audio-3.1-tts-flash-zorka_be", "qwen-audio-3.1-tts-flash-nilaav_ml", "qwen-audio-3.1-tts-flash-staer_lb", "qwen-audio-3.1-tts-flash-drita_sq", "qwen-audio-3.1-tts-flash-nila_ta", "qwen-audio-3.1-tts-flash-aruna_si", "qwen-audio-3.1-tts-flash-vennela_te", "qwen-audio-3.1-tts-flash-sade_et", "qwen-audio-3.1-tts-flash-bituon_ceb", "qwen-audio-3.1-tts-flash-vedrina_bs", "qwen-audio-3.1-tts-flash-layaung_my", "qwen-audio-3.1-tts-flash-luys_hy", "qwen-audio-3.1-tts-flash-lumen_la", "qwen-audio-3.1-tts-flash-birta_is", "qwen-audio-3.1-tts-flash-zerniq_mt", "qwen-audio-3.1-tts-flash-nuru_sw", "qwen-audio-3.1-tts-flash-arai_kk", "qwen-audio-3.1-tts-flash-zetwal_crs", "qwen-audio-3.1-tts-flash-zoria_uk"

- **`output_format`** (`string`, _optional_):
  Output audio format.
  - Default: `"mp3"`
  - Options: "mp3", "pcm", "wav", "opus"

- **`sample_rate`** (`integer`, _optional_):
  Output sample rate in Hz.
  - Default: `22050`
  - Options: 8000, 12000, 16000, 22050, 24000, 44100, 48000

- **`speed`** (`number`, _optional_):
  Speech rate multiplier.
  - Default: `1`
  - Min: 0.5
  - Max: 2

- **`pitch`** (`number`, _optional_):
  Pitch multiplier.
  - Default: `1`
  - Min: 0.5
  - Max: 2

- **`volume`** (`integer`, _optional_):
  Output volume.
  - Default: `50`
  - Min: 0
  - Max: 100

- **`bit_rate`** (`integer`, _optional_):
  Output bitrate in kbps. Applies to opus only.

- **`language_hints`** (`array[string]`, _optional_):
  Language hint list, for example ["zh"]. The upstream API only reads the first entry. Supported values: zh, en, ja, ko, fr, de, pt, it, vi, id.
  - Max items: 1

- **`instruction`** (`string`, _optional_):
  Free-style instruction controlling emotion, tone, role, dialect, or speaking style, for example "请讲上海话".
  - Default: `""`

- **`enable_ssml`** (`boolean`, _optional_):
  Treat text as SSML markup.
  - Default: `false`

- **`seed`** (`integer`, _optional_):
  Random seed for reproducible output. Use -1 for a random seed.
  - Default: `-1`
  - Min: -1
  - Max: 65535



**Required Parameters Example**:

```json
{
  "model": "alibaba/qwen-audio-3.1-tts-flash/text-to-speech",
  "text": "Welcome to Atlas Cloud — One API for All Media AI.",
  "voice": "longanhuan_v3.1"
}
```


**Full Example**:

```json
{
  "model": "alibaba/qwen-audio-3.1-tts-flash/text-to-speech",
  "text": "Welcome to Atlas Cloud — One API for All Media AI.",
  "voice": "longanhuan_v3.1",
  "output_format": "mp3",
  "sample_rate": 22050,
  "speed": 1,
  "pitch": 1,
  "volume": 50,
  "bit_rate": 0,
  "language_hints": [
    ""
  ],
  "instruction": "",
  "enable_ssml": false,
  "seed": -1
}
```


### Output Schema

The API returns the following output format:


- **`id`** (`string`, _optional_):
  Unique identifier for the prediction.

- **`model`** (`string`, _optional_):
  Model ID used for the prediction.

- **`status`** (`string`, _optional_):
  Status of the task: created, processing, completed, or failed.

- **`outputs`** (`array[string]`, _optional_):
  Array of URLs to the generated audio.

- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.



**Example Response**:

```json
{
  "id": "",
  "model": "",
  "status": "",
  "outputs": [
    ""
  ],
  "created_at": "",
  "urls": {}
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateAudio" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/qwen-audio-3.1-tts-flash/text-to-speech",
  "text": "Welcome to Atlas Cloud — One API for All Media AI.",
  "voice": "longanhuan_v3.1",
  "output_format": "mp3",
  "sample_rate": 22050,
  "speed": 1,
  "pitch": 1,
  "volume": 50,
  "bit_rate": 0,
  "language_hints": [
    ""
  ],
  "instruction": "",
  "enable_ssml": false,
  "seed": -1
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/alibaba/qwen-audio-3.1-tts-flash/text-to-speech)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### Qwen-Audio 3.1 TTS Flash

**Qwen-Audio 3.1 TTS Flash** is Alibaba's low-latency, 3.1-generation text-to-speech model. It pairs first-packet latency tuned for real-time interaction with a rich 3.1 voice catalog that covers multiple foreign languages and Chinese dialects, and it keeps free-style instruction control over emotion, tone, role, speed, and volume.

#### Why Choose This?

- **Built for real time.** Flash is tuned for first-packet latency, so it fits voice assistants, live dialogue, and customer service.
- **Multilingual and dialect voices.** The multilingual voices (`longanhuan_v3.1`, `longanlingxin_v3.1`, `longanfengyue_v3.1`, `xunanchuan_v3.1`) speak foreign languages (Japanese, Korean, French, German, Portuguese, Italian, Vietnamese, Indonesian) and Chinese dialects (Shanghainese, Cantonese, Northeastern, Chongqing, Shaanxi, Yunnan, Ningbo, Gansu).
- **Instruction control.** Use `instruction` to steer emotion, persona, or dialect (for example "请讲上海话"); use `speed`, `pitch`, and `volume` for fine control.
- **Ready-to-use audio file.** Output is mp3, pcm, wav, or opus. Billed by token (input text and output audio), matching the upstream model.

#### Parameters

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/alibaba/qwen-audio-3.1-tts-flash/text-to-speech · Docs: https://www.atlascloud.ai/docs
