# Qwen-Audio 3.1 TTS Plus MCP and API by Alibaba | FlyMy.AI

> Alibaba Qwen-Audio 3.1 TTS Plus reads text aloud in four flagship voices that speak Chinese, English, Chinese dialects and more, billed by the character.

Page: https://flymy.ai/mcp/models/qwen-audio-3-1-tts-plus/

MCP / Models / Voice, music and sound

# Qwen-Audio 3.1 TTS Plus MCP: flagship voices with dialects

Alibaba Qwen-Audio 3.1 TTS Plus reads text aloud in four flagship voices that speak Chinese, English, Chinese dialects and more, billed by the character. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use Qwen-Audio 3.1 TTS Plus](https://flymy.ai/mcp/models/qwen-audio-3-1-tts-plus/#start) [Inputs and price](https://flymy.ai/mcp/models/qwen-audio-3-1-tts-plus/#inputs)

No API key, $0.30 / 10K characters, Text to speech, Alibaba, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Qwen-Audio 3.1 TTS Plus in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

```
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/qwen-audio-3-1-tts-plus.md. Help me connect the FlyMy.AI MCP to this assistant, then run Qwen-Audio 3.1 TTS Plus (flymyai/qwen-audio-3_1-tts-plus) for this task: Read this paragraph aloud with Qwen-Audio 3.1 TTS Plus in a calm, friendly voice and send me the audio file.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/qwen-audio-3-1-tts-plus.md)

## What Qwen-Audio 3.1 TTS Plus does

Send text, up to 5,000 characters, with tags such as [excited] or [whispers] that set how the next sentences are read. voice is one of the four flagship voices, longanhuan_v3.1 by default, which speak Chinese and English and, by Alibaba's list, eight Chinese dialects and eight more languages: Japanese, Korean, French, German, Portuguese, Italian, Vietnamese and Indonesian. instruction says how to read it in plain words, such as 'Speak slowly and calmly' or a dialect; format is mp3 or wav, and rate, pitch and volume adjust the audio at no extra charge. Billing is by the character, a Chinese character counting as 2, so what a text costs is known before it runs. It has the four flagship voices only; Qwen-Audio 3.1 TTS Flash has 70. It does not clone or design voices, transcribe speech, translate or make music.

## Qwen-Audio 3.1 TTS Plus inputs

Every input of `flymyai/qwen-audio-3_1-tts-plus` as its live schema lists them. Returns `audio` (array).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/qwen-audio-3-1-tts-plus/#input-text) `text` | string required The text to read aloud, up to 5,000 characters. $0.30 per 10,000 characters; a Chinese character counts as 2, any other character as 1. Tags in the text such as [excited] or [whispers] set how the next sentences are read; [laughing] adds a sound |
| [#](https://flymy.ai/mcp/models/qwen-audio-3-1-tts-plus/#input-voice) `voice` | string optional Allowed: longanhuan_v3.1, longanlingxin_v3.1, longanfengyue_v3.1, xunanchuan_v3.1 Default: `longanhuan_v3.1` Voice id. The four flagship voices: longanhuan_v3.1 (default), longanlingxin_v3.1 and longanfengyue_v3.1 (female), xunanchuan_v3.1 (male) |
| [#](https://flymy.ai/mcp/models/qwen-audio-3-1-tts-plus/#input-instruction) `instruction` | string optional How to read the text, in plain words and in its language: pace, mood, character or a Chinese dialect, such as 'Speak slowly and calmly' or '请讲上海话。'. A slow reading makes longer speech |
| [#](https://flymy.ai/mcp/models/qwen-audio-3-1-tts-plus/#input-language_hints) `language_hints` | string optional Allowed: zh, en, fr, de, ja, ko, ru, pt, th, id, vi, es, it, ms, fil, ar The language of the text, one code, when numbers, abbreviations or symbols are read wrongly |
| [#](https://flymy.ai/mcp/models/qwen-audio-3-1-tts-plus/#input-format) `format` | string optional Allowed: mp3, wav Default: `mp3` Audio file: mp3 (default) or wav (24 kHz, 16-bit, mono) |
| [#](https://flymy.ai/mcp/models/qwen-audio-3-1-tts-plus/#input-rate) `rate` | number optional Allowed: 0.5 to 2.0 Default: `1.0` Speed of the speech: 0.5 is half, 2 is double, 1 the voice's own. The price stays the same |
| [#](https://flymy.ai/mcp/models/qwen-audio-3-1-tts-plus/#input-pitch) `pitch` | number optional Allowed: 0.5 to 2.0 Default: `1.0` Pitch, 0.5 to 2, 1 the voice's own: lower is deeper and slower, higher is higher and faster. Ignored when rate is not 1. The price stays the same |
| [#](https://flymy.ai/mcp/models/qwen-audio-3-1-tts-plus/#input-volume) `volume` | integer optional Allowed: 0 to 100 Default: `50` Loudness, 0 to 100 (50 by default) |

## Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

**“Read this paragraph aloud with Qwen-Audio 3.1 TTS Plus in a calm, friendly voice and send me the audio file.”** runs `flymyai/qwen-audio-3_1-tts-plus`

**“Voice my product demo script with Qwen-Audio 3.1 TTS Plus and give me the audio file.”** runs `flymyai/qwen-audio-3_1-tts-plus`

**“With Qwen-Audio 3.1 TTS Plus, narrate my video script slowly so I can lay the audio over the footage.”** runs `flymyai/qwen-audio-3_1-tts-plus`

## Qwen-Audio 3.1 TTS Plus price

$0.30 per 10,000 characters of text; a Chinese character counts as 2. A run at the default settings costs about $0.0026. A run costs $0.00003 to $0.30, depending on text. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

| Setting | Price |
|---|---|
| Any | $0.00003 per character |

[See usage pricing →](https://flymy.ai/pricing/)

## Call Qwen-Audio 3.1 TTS Plus from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

### From an agent, through the MCP

The agent calls `get_model_schema`, then `run_model` with:

```
{
  "endpoint_id": "flymyai/qwen-audio-3_1-tts-plus",
  "input": {
    "text": "Welcome to FlyMy.AI."
  }
}
```

### From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a `prediction_id`; read the result at `https://api.flymy.ai/api/v1/flymyai/qwen-audio-3_1-tts-plus/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/qwen-audio-3_1-tts-plus/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'text=Welcome to FlyMy.AI.'
```

## Questions about Qwen-Audio 3.1 TTS Plus

**Do I need an Alibaba API key for Qwen-Audio 3.1 TTS Plus?**

No. Qwen-Audio 3.1 TTS Plus runs on FlyMy.AI's account, so you need no Alibaba key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does Qwen-Audio 3.1 TTS Plus cost?**

$0.30 per 10,000 characters of text; a Chinese character counts as 2. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

**How do I use Qwen-Audio 3.1 TTS Plus in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Read this paragraph aloud with Qwen-Audio 3.1 TTS Plus in a calm, friendly voice and send me the audio file." Your agent reads the inputs with get_model_schema and runs flymyai/qwen-audio-3_1-tts-plus with run_model.

**What does Qwen-Audio 3.1 TTS Plus need as input?**

Qwen-Audio 3.1 TTS Plus requires text; it also takes 7 optional inputs, each listed on this page with its allowed values and default.

**Can I call Qwen-Audio 3.1 TTS Plus from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/qwen-audio-3_1-tts-plus/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

## More voice, music and sound models

Read text aloud, clone a voice from a short sample, turn lyrics or a prompt into a song, compose instrumentals, make sound effects from a description or for a video, or repair and extend a track.

### Qwen-Audio 3.1 TTS Flash

Alibaba's real-time speech model: 70 voices, Chinese dialects and an instruction that steers how it reads.

Text to speech / about $0.002 / 1K characters

Link: https://flymy.ai/mcp/models/qwen-audio-3-1-tts-flash/

### Gemini 3.8 Flash TTS

Google's higher-fidelity speech model: narration and multi-character scripts in 30 voices, with style control.

Text to speech / about $0.0135 / min of speech

Link: https://flymy.ai/mcp/models/gemini-3-8-flash-tts/

### Gemini 3.8 Flash-Lite TTS

The low-cost Gemini 3.8 speech model for high volume: read-aloud features and voice agents.

Text to speech / about $0.009 / min of speech

Link: https://flymy.ai/mcp/models/gemini-3-8-flash-lite-tts/

### Lyria 3.5

Google DeepMind's music model: full songs or instrumentals from a written brief.

Music / $0.10 / run

Link: https://flymy.ai/mcp/models/lyria-3-5-music/

### MiniMax Music 3

MiniMax's open-weights music model: lyrics and a style prompt in, a full song with vocals out.

Music / $0.002 / s

Link: https://flymy.ai/mcp/models/minimax-music-3/

### MiniMax Speech 2.8 HD

MiniMax's high-quality speech model: 332 voices, 40 languages, emotions and laughs written into the text.

Text to speech / $0.10 / 1,000 characters

Link: https://flymy.ai/mcp/models/minimax-speech-2-8-hd/

## Go to the source

[Qwen-Audio 3.1 TTS Plus in the playground →](https://app.flymy.ai/models/flymyai/qwen-audio-3_1-tts-plus), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.
