---
title: Qwen3-TTS 1.7B Base | Runware Docs
url: https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base
description: High-quality multilingual text-to-speech with voice cloning and ultra-low latency
---
# Qwen3-TTS 1.7B Base

![Qwen3-TTS 1.7B Base](https://assets.runware.ai/covers/alibaba-qwen3-tts-1-7b-base.jpg)

Qwen3-TTS 1.7B Base is the foundation text-to-speech model from Alibaba's Qwen3-TTS family. It generates human-like speech across 10+ languages including Chinese, English, Japanese, Korean, and European languages. It supports voice cloning from a 3-second audio sample and achieves latency as low as 97ms for real-time applications.

- **Status**: live
- **ID**: `alibaba:qwen@3-tts-1.7b-base`
- Try in Playground
- **Creator**: Alibaba
- **Release Date**: January 1, 2026
- **Capabilities**: Text to Audio, Checkpoint

## Pricing

$0.000015 per character · ~4s per request

**4 example generations**

- [speaker-embedding](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base/examples#example-orbital-greenhouse-intercom-ambience): `$0.0005` (~4s)
- [speaker-embedding](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base/examples#example-coffee-grounds-collection-explainer): `$0.0028` (~5s)
- [voice-cloning](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base/examples#example-rare-seed-licensing-podcast-intro): `$0.0029` (~4s)
- [voice-cloning](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base/examples#example-urban-leak-detection-explainer): `$0.0052` (~4s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/platform/pricing)

## Compatibility & Validation

When `settings.xVectorOnly` is `true`, `settings` is required.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `audioInference`

Identifier for the type of task being performed

### [taskUUID](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Audio output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-outputformat)

- **Type**: `string`
- **Default**: `MP3`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP3\`: Compressed audio, smaller file size.
- \`WAV\`: Uncompressed, high-quality audio.
- \`FLAC\`: Lossless compression.
- \`OGG\`: Open-source compressed audio format (Vorbis codec).

**Allowed values**: `MP3` `WAV` `FLAC` `OGG`

### [audioSettings](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-audiosettings)

- **Path**: `audioSettings.bitrate`
- **Type**: `object (3 properties)`

Audio encoding settings for controlling the bitrate, number of channels, and sample rate of the generated audio. Only applicable for lossy output formats (`MP3` and `OGG`). When using lossless formats (`WAV` or `FLAC`), this parameter must not be provided.

The available sample rates and valid bitrate ranges depend on the output format. For `OGG`, bitrate limits also vary by the number of channels.

**MP3 bitrate limits**:

Bitrate limits for MP3 are the same regardless of mono or stereo.

| Sample Rate | Min Bitrate | Max Bitrate |
| --- | --- | --- |
| 8,000 Hz | 8 kbps | 64 kbps |
| 11,025 Hz | 8 kbps | 64 kbps |
| 12,000 Hz | 8 kbps | 64 kbps |
| 16,000 Hz | 8 kbps | 160 kbps |
| 22,050 Hz | 8 kbps | 160 kbps |
| 24,000 Hz | 8 kbps | 160 kbps |
| 32,000 Hz | 32 kbps | 320 kbps |
| 44,100 Hz | 32 kbps | 320 kbps |
| 48,000 Hz | 32 kbps | 320 kbps |

**OGG bitrate limits — Mono (1 channel)**:

| Sample Rate | Min Bitrate | Max Bitrate |
| --- | --- | --- |
| 8,000 Hz | 8 kbps | 40 kbps |
| 12,000 Hz | 16 kbps | 48 kbps |
| 16,000 Hz | 16 kbps | 96 kbps |
| 24,000 Hz | 16 kbps | 80 kbps |
| 48,000 Hz | 32 kbps | 224 kbps |

**OGG bitrate limits — Stereo (2 channels)**:

| Sample Rate | Min Bitrate | Max Bitrate |
| --- | --- | --- |
| 8,000 Hz | 16 kbps | 80 kbps |
| 12,000 Hz | 16 kbps | 96 kbps |
| 16,000 Hz | 24 kbps | 192 kbps |
| 24,000 Hz | 32 kbps | 160 kbps |
| 48,000 Hz | 48 kbps | 256 kbps |

> [!NOTE]
> **Lossless formats**: When `outputFormat` is set to `WAV` or `FLAC`, the `audioSettings` parameter is not available since these formats produce uncompressed or lossless audio with no configurable encoding settings.

#### [bitrate](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-audiosettings-bitrate)

- **Path**: `audioSettings.bitrate`
- **Type**: `integer`
- **Min**: `8`

Audio bitrate in kbps.

#### [channels](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-audiosettings-channels)

- **Path**: `audioSettings.channels`
- **Type**: `integer`
- **Default**: `2`

Number of audio channels. 1 for mono, 2 for stereo.

**Allowed values**: `1` `2`

#### [sampleRate](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-audiosettings-samplerate)

- **Path**: `audioSettings.sampleRate`
- **Type**: `integer`

Audio sample rate in Hz.

### [webhookURL](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/platform/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns complete results directly in the API response.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/platform/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [ttl](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [audio](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-inputs-audio)

- **Path**: `inputs.audio`
- **Type**: `string`
- **Required**: true

Audio input (UUID or URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `alibaba:qwen@3-tts-1.7b-base`

Identifier of the model to use for generation.

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [speech](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-speech)

- **Path**: `speech.text`
- **Type**: `object (4 properties)`
- **Required**: true

Settings for speech generation.

#### [text](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-speech-text)

- **Path**: `speech.text`
- **Type**: `string`
- **Required**: true
- **Max**: `2000`

Text to convert to speech.

#### [voice](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-speech-voice)

- **Path**: `speech.voice`
- **Type**: `string`
- **Required**: true
- **Value**: `clone`

Voice identifier to use for speech generation.

#### [language](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-speech-language)

- **Path**: `speech.language`
- **Type**: `string`
- **Min**: `1`
- **Default**: `Auto`

Language code for speech generation.

**Allowed values**: `Auto` `Chinese` `English` `Japanese` `Korean` `German` `French` `Russian` `Portuguese` `Spanish` `Italian`

#### [speed](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-speech-speed)

- **Path**: `speech.speed`
- **Type**: `float`
- **Min**: `0.25`
- **Max**: `4`
- **Step**: `0.01`
- **Default**: `1`

Playback speed of the generated speech.

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [maxNewTokens](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-settings-maxnewtokens)

- **Path**: `settings.maxNewTokens`
- **Type**: `integer`
- **Default**: `2048`

Audio output token cap. Higher values allow longer audio but risk hangs.

### [transcript](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-settings-transcript)

- **Path**: `settings.transcript`
- **Type**: `string`

Transcript of the reference audio. Required for ICL mode, optional for x-vector-only mode.

### [xVectorOnly](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#request-settings-xvectoronly)

- **Path**: `settings.xVectorOnly`
- **Type**: `boolean`

If true, uses speaker embedding only (no transcript needed, lower similarity). If false, uses ICL mode (requires transcript, higher quality).

## Response Parameters

### [taskType](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `audioInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [audioUUID](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#response-audiouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output audio.

### [audioURL](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#response-audiourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output audio.

### [audioBase64Data](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#response-audiobase64data)

- **Type**: `string`

Base64-encoded audio data.

### [audioDataURI](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#response-audiodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output audio.

### [seed](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [cost](https://runware.ai/docs/models/alibaba-qwen3-tts-1-7b-base#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### speaker-embedding (speaker-embedding)

[Listen to audio](https://assets.runware.ai/examples/alibaba-qwen3-tts-1-7b-base/68cd37ee-ab73-44c6-88f3-764aa32f182f.wav)

> **Prompt**: Yesterday’s coffee grounds still have work to do. We collect them from local cafés and turn them into rich mushroom substrate, keeping useful material in circulation, one bucket at a time.

```json
{
  "taskType": "audioInference",
  "taskUUID": "925323c3-084b-4c81-9930-96b78535f4ad",
  "model": "alibaba:qwen@3-tts-1.7b-base",
  "speech": {
    "text": "Yesterday’s coffee grounds still have work to do. We collect them from local cafés and turn them into rich mushroom substrate, keeping useful material in circulation, one bucket at a time.",
    "voice": "clone",
    "language": "English"
  },
  "settings": {
    "xVectorOnly": true
  },
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/06a2dbe3-5891-45f1-a53b-55ccf01235fc.mp3"
  }
}
```

---

[Listen to audio](https://assets.runware.ai/examples/alibaba-qwen3-tts-1-7b-base/b6466a2b-1879-4e39-8c40-65836ae6b3f6.wav)

> **Prompt**: Chief systems log, sector C pressure seals are failing faster than predicted. We have lost exterior lights, and the aft ballast chamber is taking on water. If this message reaches the surface team, do not send the usual route divers. The trench current has shifted, and the eastern passage is no longer safe. I am sealing the lower corridor now and rerouting the last reserve power to navigation beacons. Crew status: four accounted for, one missing near the research bay. Oxygen remains limited, but we still have a narrow window to ascend if the port thrusters answer on the next cycle. Mark this transmission urgent, and tell Mira her star charts were right about the magnetic drift.

```json
{
  "taskType": "audioInference",
  "taskUUID": "80bf30e0-af7b-45ad-aa44-abaa7b5993dd",
  "model": "alibaba:qwen@3-tts-1.7b-base",
  "speech": {
    "text": "Chief systems log, sector C pressure seals are failing faster than predicted. We have lost exterior lights, and the aft ballast chamber is taking on water. If this message reaches the surface team, do not send the usual route divers. The trench current has shifted, and the eastern passage is no longer safe. I am sealing the lower corridor now and rerouting the last reserve power to navigation beacons. Crew status: four accounted for, one missing near the research bay. Oxygen remains limited, but we still have a narrow window to ascend if the port thrusters answer on the next cycle. Mark this transmission urgent, and tell Mira her star charts were right about the magnetic drift.",
    "voice": "clone",
    "language": "English",
    "speed": 0.92
  },
  "settings": {
    "transcript": "Engine room status nominal. Pressure remains stable across the lower hull, and backup pumps are online. We should reach the trench marker in eight minutes.",
    "xVectorOnly": false,
    "maxNewTokens": 2048
  },
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/69e7eb9b-918e-4253-80f9-341b517ce3f7.mp3"
  }
}
```

---

### voice-cloning (voice-cloning)

[Listen to audio](https://assets.runware.ai/examples/alibaba-qwen3-tts-1-7b-base/3546274e-4d01-4ed3-ad05-97856cf6cb45.wav)

> **Prompt**: Welcome to Field Rights. Today, we follow a drought-tolerant sorghum trait from a university greenhouse to a licensing dispute in Kansas—and ask when public research becomes private leverage.

```json
{
  "taskType": "audioInference",
  "taskUUID": "5a17d95d-011c-45b8-8380-1fc98bb5d89b",
  "model": "alibaba:qwen@3-tts-1.7b-base",
  "speech": {
    "text": "Welcome to Field Rights. Today, we follow a drought-tolerant sorghum trait from a university greenhouse to a licensing dispute in Kansas—and ask when public research becomes private leverage.",
    "voice": "clone",
    "language": "English"
  },
  "settings": {
    "transcript": "Today, the morning light made every familiar street feel new again.",
    "xVectorOnly": false
  },
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/23b5f12c-dd5c-4cf1-882b-65d9c33bd790.mp3"
  }
}
```

---

### speaker-embedding (speaker-embedding)

[Listen to audio](https://assets.runware.ai/examples/alibaba-qwen3-tts-1-7b-base/7f6ad73d-ac97-4a2c-9085-3ae6c2181243.wav)

> **Prompt**: 水耕栽培区画の散水を開始します。通路の青い表示線から離れてください。

```json
{
  "taskType": "audioInference",
  "taskUUID": "45b97d4d-4dff-4cf0-b2af-f8187f7e4536",
  "model": "alibaba:qwen@3-tts-1.7b-base",
  "speech": {
    "text": "水耕栽培区画の散水を開始します。通路の青い表示線から離れてください。",
    "voice": "clone",
    "language": "Japanese"
  },
  "settings": {
    "xVectorOnly": true
  },
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/17e50fde-abe7-47ee-a9a3-5175214461af.mp3"
  }
}
```

---

[Listen to audio](https://assets.runware.ai/examples/alibaba-qwen3-tts-1-7b-base/9d35c539-de62-4eec-9c1e-0031a4445b5f.wav)

> **Prompt**: Attention passengers on Platform 4. The northbound sleeper service to Alder's End will arrive shortly. Please stand behind the yellow line, keep your luggage close, and have your tickets ready for inspection. Due to heavy fog beyond the river crossing, departure will be delayed by approximately twelve minutes. We appreciate your patience and wish you a comfortable journey tonight.

```json
{
  "taskType": "audioInference",
  "taskUUID": "ae6db1bc-c6b9-4796-abd4-7abd7eb9c7f4",
  "model": "alibaba:qwen@3-tts-1.7b-base",
  "speech": {
    "text": "Attention passengers on Platform 4. The northbound sleeper service to Alder's End will arrive shortly. Please stand behind the yellow line, keep your luggage close, and have your tickets ready for inspection. Due to heavy fog beyond the river crossing, departure will be delayed by approximately twelve minutes. We appreciate your patience and wish you a comfortable journey tonight.",
    "voice": "clone",
    "language": "English",
    "speed": 0.96
  },
  "settings": {
    "transcript": "Good evening. This is a sample of my speaking voice for cloning. The weather is cool tonight, and the station is quiet except for distant rails and footsteps.",
    "xVectorOnly": false,
    "maxNewTokens": 2048
  },
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/9d10ac76-7767-4393-a125-92308c291e70.mp3"
  }
}
```

---

[Listen to audio](https://assets.runware.ai/examples/alibaba-qwen3-tts-1-7b-base/15931a8a-78b1-4935-bbe0-0f7509759e93.wav)

> **Prompt**: Station Delta, this is Dr. Elian Voss with the six a.m. ice shelf briefing. Surface temperature has risen by point eight degrees overnight, and the western fracture line is now advancing faster than projected. Team A will relocate the sensor sleds to ridge marker twelve. Team B should suspend drilling until the tremor pattern settles. If you are crossing the blue corridor, keep thirty meters between vehicles and confirm every checkpoint by radio. Visibility is excellent, but the ground layer remains unstable beneath the new crust. Repeat: excellent visibility, unstable ground layer. Upload all core scans before thirteen hundred. We may have a narrow window to capture the deep thermal shift before the shelf resets.

```json
{
  "taskType": "audioInference",
  "taskUUID": "ded49ad4-d6f5-4ea8-a327-1f43abf6d4fa",
  "model": "alibaba:qwen@3-tts-1.7b-base",
  "speech": {
    "text": "Station Delta, this is Dr. Elian Voss with the six a.m. ice shelf briefing. Surface temperature has risen by point eight degrees overnight, and the western fracture line is now advancing faster than projected. Team A will relocate the sensor sleds to ridge marker twelve. Team B should suspend drilling until the tremor pattern settles. If you are crossing the blue corridor, keep thirty meters between vehicles and confirm every checkpoint by radio. Visibility is excellent, but the ground layer remains unstable beneath the new crust. Repeat: excellent visibility, unstable ground layer. Upload all core scans before thirteen hundred. We may have a narrow window to capture the deep thermal shift before the shelf resets.",
    "voice": "clone",
    "language": "English",
    "speed": 0.93
  },
  "settings": {
    "transcript": "Good morning team, this is Dr. Elian Voss checking comms before the first survey run. Conditions are stable for departure, so keep your channels open and report any anomalies immediately.",
    "xVectorOnly": false,
    "maxNewTokens": 2048
  },
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/a4c0d1d9-072f-4939-a167-710c91e58717.mp3"
  }
}
```

---

### voice-cloning (voice-cloning)

[Listen to audio](https://assets.runware.ai/examples/alibaba-qwen3-tts-1-7b-base/59a1c4da-f9a1-4c90-a883-dd7e0128e489.wav)

> **Prompt**: Una fuga subterránea puede pasar meses sin verse, pero no sin escucharse. Nuestros sensores acústicos analizan la red durante la noche, identifican sonidos anómalos y señalan el tramo exacto que necesita atención. Así, el equipo municipal puede reparar antes, excavar menos y evitar que miles de litros de agua potable se pierdan bajo la ciudad.

```json
{
  "taskType": "audioInference",
  "taskUUID": "cacdb98b-1d02-4048-92be-7e7e21be706e",
  "model": "alibaba:qwen@3-tts-1.7b-base",
  "speech": {
    "text": "Una fuga subterránea puede pasar meses sin verse, pero no sin escucharse. Nuestros sensores acústicos analizan la red durante la noche, identifican sonidos anómalos y señalan el tramo exacto que necesita atención. Así, el equipo municipal puede reparar antes, excavar menos y evitar que miles de litros de agua potable se pierdan bajo la ciudad.",
    "voice": "clone",
    "language": "Spanish"
  },
  "settings": {
    "transcript": "Today, the morning light made every familiar street feel new again.",
    "xVectorOnly": false
  },
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/9c7e0f15-6070-4526-a1fc-41013cad9e81.mp3"
  }
}
```

---

[Listen to audio](https://assets.runware.ai/examples/alibaba-qwen3-tts-1-7b-base/002afe59-ec45-4b3d-819c-0f2bc3014f24.wav)

> **Prompt**: Good evening, and welcome to Gallery Seven. Outside, the rain taps softly against the tall glass panes, but in here the room stays hushed, warm, and full of suspended attention. Before you is a weathered bronze astrolabe recovered from a river crossing centuries ago. Notice the worn edge near the lower ring; that smoothness came not from time alone, but from repeated handling by navigators who trusted it during long journeys. As you move closer, look for the tiny engraved star marks arranged in uneven arcs. They are easy to miss at first, yet they reveal how practical knowledge and artistry once lived side by side. When you are ready, continue to the next display, where a series of field journals records the same route in three different seasons.

```json
{
  "taskType": "audioInference",
  "taskUUID": "58703dfd-8d1b-46f2-8efd-8ef2a9f23fdd",
  "model": "alibaba:qwen@3-tts-1.7b-base",
  "speech": {
    "text": "Good evening, and welcome to Gallery Seven. Outside, the rain taps softly against the tall glass panes, but in here the room stays hushed, warm, and full of suspended attention. Before you is a weathered bronze astrolabe recovered from a river crossing centuries ago. Notice the worn edge near the lower ring; that smoothness came not from time alone, but from repeated handling by navigators who trusted it during long journeys. As you move closer, look for the tiny engraved star marks arranged in uneven arcs. They are easy to miss at first, yet they reveal how practical knowledge and artistry once lived side by side. When you are ready, continue to the next display, where a series of field journals records the same route in three different seasons.",
    "voice": "clone",
    "language": "English",
    "speed": 0.93
  },
  "settings": {
    "maxNewTokens": 2048,
    "transcript": "Welcome. Please follow me to the next gallery for a closer look.",
    "xVectorOnly": false
  },
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/6e19ca15-d4dc-4a2e-ba62-6d39e7d2e8b5.mp3"
  }
}
```