# Qwen 3 TTS - Voice Design [1.7B] > Create custom voices using Qwen3-TTS Voice Design model and later use Clone Voice model to create your own voices! ## Overview - **Endpoint**: `https://fal.run/fal-ai/qwen-3-tts/voice-design/1.7b` - **Model ID**: `fal-ai/qwen-3-tts/voice-design/1.7b` - **Category**: text-to-speech - **Kind**: inference **Tags**: text-to-speech, voice-design ## Pricing - **Price**: $0.09 per 1000 characters For more details, see [fal.ai pricing](https://fal.ai/pricing). ## API Information This model can be used via our HTTP API or more conveniently via our client libraries. See the input and output schema below, as well as the usage examples. ### Input Schema The API accepts the following input parameters: - **`text`** (`string`, _required_): The text to be converted to speech. - Examples: "It's in the top drawer... wait, it's empty? No way, that's impossible! I'm sure I put it there!" - **`language`** (`LanguageEnum`, _optional_): The language of the voice to be designed. Default value: `"Auto"` - Default: `"Auto"` - Options: `"Auto"`, `"English"`, `"Chinese"`, `"Spanish"`, `"French"`, `"German"`, `"Italian"`, `"Japanese"`, `"Korean"`, `"Portuguese"`, `"Russian"` - Examples: "English" - **`prompt`** (`string`, _required_): Optional prompt to guide the style of the generated speech. - Examples: "Speak in an incredulous tone, but with a hint of panic beginning to creep into your voice." - **`top_k`** (`integer`, _optional_): Top-k sampling parameter. Default value: `50` - Default: `50` - **`top_p`** (`float`, _optional_): Top-p sampling parameter. Default value: `1` - Default: `1` - Range: `0` to `1` - **`temperature`** (`float`, _optional_): Sampling temperature; higher => more random. Default value: `0.9` - Default: `0.9` - Range: `0` to `1` - **`repetition_penalty`** (`float`, _optional_): Penalty to reduce repeated tokens/codes. Default value: `1.05` - Default: `1.05` - **`subtalker_dosample`** (`boolean`, _optional_): Sampling switch for the sub-talker. Default value: `true` - Default: `true` - **`subtalker_top_k`** (`integer`, _optional_): Top-k for sub-talker sampling. Default value: `50` - Default: `50` - **`subtalker_top_p`** (`float`, _optional_): Top-p for sub-talker sampling. Default value: `1` - Default: `1` - Range: `0` to `1` - **`subtalker_temperature`** (`float`, _optional_): Temperature for sub-talker sampling. Default value: `0.9` - Default: `0.9` - Range: `0` to `1` - **`max_new_tokens`** (`integer`, _optional_): Maximum number of new codec tokens to generate. Default value: `200` - Default: `200` - Range: `1` to `8192` **Required Parameters Example**: ```json { "text": "It's in the top drawer... wait, it's empty? No way, that's impossible! I'm sure I put it there!", "prompt": "Speak in an incredulous tone, but with a hint of panic beginning to creep into your voice." } ``` **Full Example**: ```json { "text": "It's in the top drawer... wait, it's empty? No way, that's impossible! I'm sure I put it there!", "language": "English", "prompt": "Speak in an incredulous tone, but with a hint of panic beginning to creep into your voice.", "top_k": 50, "top_p": 1, "temperature": 0.9, "repetition_penalty": 1.05, "subtalker_dosample": true, "subtalker_top_k": 50, "subtalker_top_p": 1, "subtalker_temperature": 0.9, "max_new_tokens": 200 } ``` ### Output Schema The API returns the following output format: - **`audio`** (`AudioFile`, _required_): The generated speech audio file. - Examples: {"url":"https://storage.googleapis.com/falserverless/example_outputs/qwen3-tts/design_out.mp3","channels":1,"duration":7.736875,"content_type":"audio/mpeg","file_name":"rHFLVApz9Rdenm20UvnGf_FtjmMLBV.mp3","sample_rate":24000} **Example Response**: ```json { "audio": { "url": "https://storage.googleapis.com/falserverless/example_outputs/qwen3-tts/design_out.mp3", "channels": 1, "duration": 7.736875, "content_type": "audio/mpeg", "file_name": "rHFLVApz9Rdenm20UvnGf_FtjmMLBV.mp3", "sample_rate": 24000 } } ``` ## Usage Examples ### cURL ```bash curl --request POST \ --url https://fal.run/fal-ai/qwen-3-tts/voice-design/1.7b \ --header "Authorization: Key $FAL_KEY" \ --header "Content-Type: application/json" \ --data '{ "text": "It's in the top drawer... wait, it's empty? No way, that's impossible! I'm sure I put it there!", "prompt": "Speak in an incredulous tone, but with a hint of panic beginning to creep into your voice." }' ``` ### Python Ensure you have the Python client installed: ```bash pip install fal-client ``` Then use the API client to make requests: ```python import fal_client def on_queue_update(update): if isinstance(update, fal_client.InProgress): for log in update.logs: print(log["message"]) result = fal_client.subscribe( "fal-ai/qwen-3-tts/voice-design/1.7b", arguments={ "text": "It's in the top drawer... wait, it's empty? No way, that's impossible! I'm sure I put it there!", "prompt": "Speak in an incredulous tone, but with a hint of panic beginning to creep into your voice." }, with_logs=True, on_queue_update=on_queue_update, ) print(result) ``` ### JavaScript Ensure you have the JavaScript client installed: ```bash npm install --save @fal-ai/client ``` Then use the API client to make requests: ```javascript import { fal } from "@fal-ai/client"; const result = await fal.subscribe("fal-ai/qwen-3-tts/voice-design/1.7b", { input: { text: "It's in the top drawer... wait, it's empty? No way, that's impossible! I'm sure I put it there!", prompt: "Speak in an incredulous tone, but with a hint of panic beginning to creep into your voice." }, logs: true, onQueueUpdate: (update) => { if (update.status === "IN_PROGRESS") { update.logs.map((log) => log.message).forEach(console.log); } }, }); console.log(result.data); console.log(result.requestId); ``` ## Additional Resources ### Documentation - [Model Playground](https://fal.ai/models/fal-ai/qwen-3-tts/voice-design/1.7b) - [API Documentation](https://fal.ai/models/fal-ai/qwen-3-tts/voice-design/1.7b/api) - [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=fal-ai/qwen-3-tts/voice-design/1.7b) ### fal.ai Platform - [Platform Documentation](https://docs.fal.ai) - [Python Client](https://docs.fal.ai/clients/python) - [JavaScript Client](https://docs.fal.ai/clients/javascript)