MODEL ID alibaba:qwen@3-tts-1.7b-voicedesign

live

Qwen3-TTS 1.7B VoiceDesign

by Alibaba January 1, 2026

Qwen3-TTS 1.7B VoiceDesign is a text-to-speech model from Alibaba that creates custom voices from natural language descriptions specifying emotion, tone, and prosody. It supports voice cloning from a 3-second audio sample, generates speech in 10+ languages including Chinese, English, Japanese, Korean, and European languages, and achieves latency as low as 97ms.

API Options

Platform-level options for task execution and delivery.

taskType string required value: audioInference: Identifier for the type of task being performed

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

outputType string default: URL: Audio output type.

Allowed values 3 values

outputFormat 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 4 values

audioSettings object

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

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.

Properties 3 properties

audioSettings » bitrate bitrate integer min: 8: Audio bitrate in kbps.

audioSettings » channels channels integer default: 2: Number of audio channels. 1 for mono, 2 for stereo.

Allowed values 2 values

audioSettings » sampleRate sampleRate integer: Audio sample rate in Hz.

webhookURL string 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
PLATFORM

deliveryMethod string default: sync

Determines how the API delivers task results.

Allowed values 2 values

: Returns complete results directly in the API response.
: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

Learn more 1 resource

Task Polling
PLATFORM

uploadEndpoint string 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.

// 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 integer min: 60: Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

includeCost boolean default: false: Include task cost in the response.

numberResults integer min: 1 max: 4 default: 1: Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

Generation Parameters

Core parameters for controlling the generated content.

model string required value: alibaba:qwen@3-tts-1.7b-voicedesign

Identifier of the model to use for generation.

Learn more 3 resources

positivePrompt string required

Natural language voice description. Example: 'A warm, cheerful male voice with moderate pace'.

Learn more 2 resources

speech object required

Settings for speech generation.

Properties 4 properties

speech » text text string required max: 2000: Text to convert to speech.

speech » voice voice string required value: design: Voice identifier to use. Set to auto for automatic selection.

speech » language language string min: 1 default: Auto: Language code for speech generation.

Allowed values 11 values

speech » speed speed 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.

settings » maxNewTokens maxNewTokens integer default: 2048: Audio output token cap. Higher values allow longer audio but risk hangs.

taskType string required value: audioInference: Type of the task.

taskUUID string required UUID v4: UUID of the task.

audioUUID string required UUID v4: UUID of the output audio.

audioURL string URI: URL of the output audio.

audioBase64Data string: Base64-encoded audio data.

audioDataURI string URI: Data URI of the output audio.

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

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

Text to Audio

Museum Planetarium Audio Guide

{
  "taskType": "audioInference",
  "taskUUID": "7a687894-17db-4452-a7c4-87929a5f31a7",
  "audioUUID": "7aab316a-f086-4cbd-80ad-0125f4311c04",
  "audioURL": "https://am.runware.ai/audio/os/a15d18/ws/5/ai/7aab316a-f086-4cbd-80ad-0125f4311c04.wav",
  "cost": 0.0004
}

Request

{
  "taskType": "audioInference",
  "taskUUID": "7a687894-17db-4452-a7c4-87929a5f31a7",
  "model": "alibaba:qwen@3-tts-1.7b-voicedesign",
  "positivePrompt": "A composed, knowledgeable female voice in her forties with a clear international English accent, gentle resonance, measured pacing, and soft breath control. The tone is welcoming and intellectually curious, like a senior museum guide leading visitors beneath a domed star theater. Subtle awe on cosmic phrases, crisp diction on scientific terms, never theatrical, never robotic. Warm, polished, intimate public-speaking quality with natural pauses and graceful sentence endings.",
  "speech": {
    "text": "Welcome to the Hall of Ancient Skies. Above you, the ceiling recreates the winter constellations as they were charted over a thousand years ago. Notice how Orion stands slightly tilted compared with modern maps; this projection follows the perspective used by navigators who crossed open water with nothing but memory, geometry, and nerve. To your left is a bronze armillary sphere, its rings modeling the heavens as a set of interlocking paths. It is not only an instrument, but a theory made visible. As the lights dim, watch the red point near the horizon. That is Mars, rendered as it appeared during a famously bright opposition. For many cultures, such moments were more than astronomical events. They were signals, arguments, omens, and invitations to ask a daring question: if the sky changes, what else might change with it?",
    "voice": "design",
    "language": "English",
    "speed": 0.94
  },
  "settings": {
    "maxNewTokens": 2048
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "7a687894-17db-4452-a7c4-87929a5f31a7",
  "audioUUID": "7aab316a-f086-4cbd-80ad-0125f4311c04",
  "audioURL": "https://am.runware.ai/audio/os/a15d18/ws/5/ai/7aab316a-f086-4cbd-80ad-0125f4311c04.wav",
  "cost": 0.0004
}

Text to Audio

After-Hours Train Platform Monologue

{
  "taskType": "audioInference",
  "taskUUID": "cab3d9ce-4e46-45f3-a82e-9934483ce13d",
  "audioUUID": "d2b86525-9c38-4409-a9ca-c8964cdf34c0",
  "audioURL": "https://am.runware.ai/audio/os/a22d05/ws/5/ai/d2b86525-9c38-4409-a9ca-c8964cdf34c0.wav",
  "cost": 0.0002
}

Request

{
  "taskType": "audioInference",
  "taskUUID": "cab3d9ce-4e46-45f3-a82e-9934483ce13d",
  "model": "alibaba:qwen@3-tts-1.7b-voicedesign",
  "positivePrompt": "A middle-aged female voice with low, smoky warmth and precise diction, sounding like a veteran rail announcer speaking after a very long shift. Calm, intimate, slightly tired, with understated empathy rather than cheerfulness. Medium-slow pace, gentle breath between sentences, soft downward inflections, subtle urban accent, clear consonants, natural pauses, and a reflective late-night atmosphere.",
  "speech": {
    "text": "Last service to Briar End now arriving on platform four. Please stand back from the edge and let passengers leave the train first. If you missed your connection, speak to the night desk beside the main exit. They can help with onward travel, warm waiting areas, and hotel information. To the person who left a blue notebook near the ticket machines, it has been handed in. And to everyone still making their way home, take your time, keep your belongings close, and travel safely tonight.",
    "voice": "design",
    "language": "English",
    "speed": 0.94
  },
  "settings": {
    "maxNewTokens": 2048
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "cab3d9ce-4e46-45f3-a82e-9934483ce13d",
  "audioUUID": "d2b86525-9c38-4409-a9ca-c8964cdf34c0",
  "audioURL": "https://am.runware.ai/audio/os/a22d05/ws/5/ai/d2b86525-9c38-4409-a9ca-c8964cdf34c0.wav",
  "cost": 0.0002
}

Text to Audio

Late-Night Pirate Radio Host

{
  "taskType": "audioInference",
  "taskUUID": "b4fdc8b4-0fbb-4c12-93b0-210198bf639d",
  "audioUUID": "8f497a6c-71f8-4258-ae22-3d1ab0898473",
  "audioURL": "https://am.runware.ai/audio/os/a04d20/ws/5/ai/8f497a6c-71f8-4258-ae22-3d1ab0898473.wav",
  "cost": 0.0004
}

Request

{
  "taskType": "audioInference",
  "taskUUID": "b4fdc8b4-0fbb-4c12-93b0-210198bf639d",
  "model": "alibaba:qwen@3-tts-1.7b-voicedesign",
  "positivePrompt": "A husky middle-aged voice with magnetic late-night radio presence, lightly worn texture, intimate microphone closeness, dry humor, sharp diction, and a confidential tone that occasionally blooms into theatrical emphasis. Moderate pace with purposeful pauses, slightly lowered pitch, relaxed breath control, and the feeling of someone speaking to insomniacs across a sleeping city from a cramped rooftop studio.",
  "speech": {
    "text": "Good morning to the bakers, the coders, the taxi drivers, and everyone else keeping odd hours. You’ve found Channel Nine Point Three, the station that survives on stubborn wiring and borrowed coffee. Tonight’s question comes from a listener who swears the old freight elevator in Building C stops on a floor that does not exist on any plan. Now, I’m not saying I believe in phantom architecture. I’m saying that if a brass gate opens where a concrete wall should be, you take notes before you panic. So if you’re out there with a flashlight, a notebook, and regrettable curiosity, call in. Tell me what the air smelled like. Tell me whether the numbers above the door were painted or burned in. And most importantly, tell me if the music was already playing before the elevator arrived.",
    "voice": "design",
    "language": "English",
    "speed": 0.96
  },
  "settings": {
    "maxNewTokens": 2048
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "b4fdc8b4-0fbb-4c12-93b0-210198bf639d",
  "audioUUID": "8f497a6c-71f8-4258-ae22-3d1ab0898473",
  "audioURL": "https://am.runware.ai/audio/os/a04d20/ws/5/ai/8f497a6c-71f8-4258-ae22-3d1ab0898473.wav",
  "cost": 0.0004
}

Text to Audio

Crackling Lighthouse Weather Bulletin

{
  "taskType": "audioInference",
  "taskUUID": "60fb0d36-54c6-41b7-bd98-d884ea171b49",
  "audioUUID": "c372cc9d-8905-4930-95c0-2564c65f7a53",
  "audioURL": "https://am.runware.ai/audio/os/a11d13/ws/5/ai/c372cc9d-8905-4930-95c0-2564c65f7a53.wav",
  "cost": 0.0003
}

Request

{
  "taskType": "audioInference",
  "taskUUID": "60fb0d36-54c6-41b7-bd98-d884ea171b49",
  "model": "alibaba:qwen@3-tts-1.7b-voicedesign",
  "positivePrompt": "A weathered middle-aged radio announcer voice with a faint maritime rasp, calm under pressure, clear diction, low-to-mid pitch, measured pacing, subtle analog broadcast character, reassuring but urgent, as if speaking from a remote lighthouse station during rough seas.",
  "speech": {
    "text": "Attention all small craft in the outer bay. Wind has shifted hard to the northeast and visibility is falling fast beyond the shoals. Repeat, visibility is dropping fast. If you can see the white tower, keep it off your port side and reduce speed before the rocks. Larger swells are arriving in uneven sets, and the channel markers may sound closer than they are. Harbor control reports one tug outbound at first light, but no additional escort tonight. Secure loose gear, check your compass twice, and answer on channel sixteen if you require guidance. This is Greycap Light Station, standing by.",
    "voice": "design",
    "language": "English",
    "speed": 0.96
  },
  "settings": {
    "maxNewTokens": 2048
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "60fb0d36-54c6-41b7-bd98-d884ea171b49",
  "audioUUID": "c372cc9d-8905-4930-95c0-2564c65f7a53",
  "audioURL": "https://am.runware.ai/audio/os/a11d13/ws/5/ai/c372cc9d-8905-4930-95c0-2564c65f7a53.wav",
  "cost": 0.0003
}