# Alibaba Qwen 3 TTS - Text to Speech [1.7B] API

> Qwen 3 Tts 1.7b is Alibaba's text-to-speech AI model. Generate human-like voiceovers with expressive intonation, multilingual support, and customizable voice characteristics.

Source: https://www.sandbase.ai/models/alibaba/qwen-3-tts/1.7b
API reference: https://www.sandbase.ai/models/alibaba/qwen-3-tts/1.7b/docs

## Facts

- Provider: Alibaba
- Type: Audio model
- Model ID: `alibaba/qwen-3-tts/1.7b`
- Price: From $0.0001 per run
- Capabilities: text to speech
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

- Unified Run API: `POST https://api.sandbase.ai/v1/run`

```bash
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/qwen-3-tts/1.7b",
  "text": "I am solving the equation: x = [-b ± √(b²-4ac)] / 2a? Nobody can — it'"'"'s a disaster (◍•͈⌔•͈◍), very sad!",
  "top_k": 50,
  "top_p": 1,
  "voice": "Vivian",
  "prompt": "Very happy.",
  "language": "English",
  "temperature": 0.9,
  "max_new_tokens": 200,
  "reference_text": "Okay. Yeah. I resent you. I love you. I respect you. But you know what? You blew it! And it is all thanks to you.",
  "subtalker_top_k": 50,
  "subtalker_top_p": 1,
  "repetition_penalty": 1.05,
  "subtalker_dosample": true,
  "subtalker_temperature": 0.9,
  "speaker_voice_embedding_file_url": "https://static.sandbase.ai/examples/alibaba/qwen-3-tts/1.7b/output_url_0.safetensors"
}'
```

The response returns a run id; poll `GET https://api.sandbase.ai/v1/run/{id}` until the status is `completed` or `failed`.

## FAQ

### How do I call Alibaba Qwen 3 TTS - Text to Speech [1.7B] through SandBase?

Create a SandBase API key, then send requests with the model ID "alibaba/qwen-3-tts/1.7b" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

### Do I need a separate Alibaba account?

No. One SandBase API key and balance gives you access to Alibaba Qwen 3 TTS - Text to Speech [1.7B] and the other models in the catalog; you do not need to sign up with Alibaba separately.

## README

### Qwen 3 TTS - Text to Speech [1.7B]

Qwen 3 TTS 1.7B, the open-weights Qwen speech model: text to speech in 10 languages with nine preset voices, or a cloned voice from a speaker-embedding file. The 1.7B model gives more natural prosody than 0.6B.

#### Fields

| Field | Type | Default | Notes |
|---|---|---|---|
| `prompt` | string, required | — | Text to speak. |
| `text` | string | — | Alias of `prompt`; if both are sent, `text` is used. |
| `subtalker_temperature` | number 0–1 | 0.9 | Sub-model temperature. |
| `speaker_voice_embedding_file_url` | string | — | Optional cloned-voice embedding (safetensors) to use instead of a preset voice. |
| `repetition_penalty` | number | 1.05 | Reduces repeated sounds. |
| `language` | `Auto` / `English` / `Chinese` / `Spanish` / `French` / `German` / `Italian` / `Japanese` / `Korean` / `Portuguese` / `Russian` | `Auto` | Spoken language; `Auto` detects it. |
| `subtalker_top_p` | number 0–1 | 1 | Sub-model sampling setting. |
| `top_p` | number 0–1 | 1 | Sampling setting. |
| `reference_text` | string | — | Transcript used when the embedding was created; improves cloned-voice quality. |
| `top_k` | integer | 50 | Sampling setting; leave at default unless delivery is unstable. |
| `subtalker_top_k` | integer | 50 | Sub-model sampling setting. |
| `temperature` | number 0–1 | 0.9 | Higher values give more varied delivery. |
| `voice` | `Vivian` / `Serena` / `Uncle_Fu` / `Dylan` / `Eric` / `Ryan` / `Aiden` / `Ono_Anna` / `Sohee` | — | Preset voice; ignored when a speaker embedding is supplied. |
| `max_new_tokens` | integer 1–8192 | 200 | Caps the generated audio length; raise it for long text. |
| `subtalker_dosample` | boolean | true | Sampling switch for the acoustic sub-model. |

#### Billing

$0.09 per 1,000 characters of input text, billed per character.

| Text | Price |
|---|---|
| 100 characters | $0.009 |
| 1,000 characters | $0.09 |
| 5,000 characters | $0.45 |

Failed runs are not charged.

#### Prompting

- Use punctuation to control pauses; break long passages into paragraphs.
- Pick a voice whose primary language matches the text.

#### Limits

- `max_new_tokens` (default 200) caps the audio length; long text needs a higher value.

#### Also on SandBase

Related: `alibaba/qwen-3-tts/0.6b`.