usamaehsan/qwen3-tts-voice-design

Text-to-speech in a new voice designed from a text description (10 languages). Qwen3-TTS VoiceDesign, Apache-2.0. No audio input, no cloning; descriptions that name a real person are refused.

Public
14 runs

Run usamaehsan/qwen3-tts-voice-design with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
text
string
Text to speak (up to 1500 characters).
voice_description
string
Describe the voice in words: age, gender, tone, pace, accent, character. Example: 'A warm older British man, deep and slightly raspy, a slow bedtime storyteller.' Naming a real person is refused; this model designs new voices, it does not copy people.
language
None
auto
Language of the text. 'auto' detects it.
max_seconds
number
60

Min: 1.0

Max: 120.0

Longest audio to make, in seconds.
temperature
number
0.9

Min: 0.1

Max: 1.5

Sampling temperature. Lower = steadier, higher = more varied.
seed
integer
Random seed. Same seed + same inputs = same voice.
output_format
None
mp3
Audio format.

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "string",
  "title": "Output",
  "format": "uri"
}