Custom Voice 17B
The client provides a convenient way to interact with the model API.
npm install --save @fal-ai/clientThe @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Install the new package and update your imports — see client setup.
Set FAL_KEY as an environment variable in your runtime.
export FAL_KEY="YOUR_API_KEY"The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.
import { fal } from "@fal-ai/client";
const result = await fal.subscribe("fal-ai/qwen-3-tts/text-to-speech/1.7b", {
input: {
text: "I am solving the equation: x = [-b ± √(b²-4ac)] / 2a? Nobody can — it's a disaster (◍•͈⌔•͈◍), very sad!"
},
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);The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.
import { fal } from "@fal-ai/client";
fal.config({
credentials: "YOUR_FAL_KEY"
});When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.
The client API provides a convenient way to submit requests to the model.
import { fal } from "@fal-ai/client";
const { request_id } = await fal.queue.submit("fal-ai/qwen-3-tts/text-to-speech/1.7b", {
input: {
text: "I am solving the equation: x = [-b ± √(b²-4ac)] / 2a? Nobody can — it's a disaster (◍•͈⌔•͈◍), very sad!"
},
webhookUrl: "https://optional.webhook.url/for/results",
});You can fetch the status of a request to check if it is completed or still in progress.
import { fal } from "@fal-ai/client";
const status = await fal.queue.status("fal-ai/qwen-3-tts/text-to-speech/1.7b", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
logs: true,
});Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.
import { fal } from "@fal-ai/client";
const result = await fal.queue.result("fal-ai/qwen-3-tts/text-to-speech/1.7b", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.
You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.
You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.
We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.
import { fal } from "@fal-ai/client";
const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).
Read more about file handling in our file upload guide.
text string* requiredThe text to be converted to speech.
prompt stringOptional prompt to guide the style of the generated speech. This prompt will be ignored if a speaker embedding is provided.
voice EnumThe voice to be used for speech synthesis, will be ignored if a speaker embedding is provided. Check out the documentation for each voice's details and which language they primarily support.
Possible enum values: Vivian, Serena, Uncle_Fu, Dylan, Eric, Ryan, Aiden, Ono_Anna, Sohee
language LanguageEnumThe language of the voice. Default value: "Auto"
Possible enum values: Auto, English, Chinese, Spanish, French, German, Italian, Japanese, Korean, Portuguese, Russian
speaker_voice_embedding_file_url stringURL to a speaker embedding file in safetensors format, from fal-ai/qwen-3-tts/clone-voice endpoint. If provided, the TTS model will use the cloned voice for synthesis instead of the predefined voices.
reference_text stringOptional reference text that was used when creating the speaker embedding. Providing this can improve synthesis quality when using a cloned voice.
top_k integerTop-k sampling parameter. Default value: 50
top_p floatTop-p sampling parameter. Default value: 1
temperature floatSampling temperature; higher => more random. Default value: 0.9
repetition_penalty floatPenalty to reduce repeated tokens/codes. Default value: 1.05
subtalker_dosample booleanSampling switch for the sub-talker. Default value: true
subtalker_top_k integerTop-k for sub-talker sampling. Default value: 50
subtalker_top_p floatTop-p for sub-talker sampling. Default value: 1
subtalker_temperature floatTemperature for sub-talker sampling. Default value: 0.9
max_new_tokens integerMaximum number of new codec tokens to generate. Default value: 200
enable_safety_checker booleanAuthorized callers may set false to request relaxed screening. Default value: true
{
"text": "I am solving the equation: x = [-b ± √(b²-4ac)] / 2a? Nobody can — it's a disaster (◍•͈⌔•͈◍), very sad!",
"prompt": "Very happy.",
"voice": "Vivian",
"language": "English",
"speaker_voice_embedding_file_url": "https://storage.googleapis.com/falserverless/example_outputs/qwen3-tts/clone_out.safetensors",
"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.",
"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,
"enable_safety_checker": true
}The generated speech audio file.
{
"audio": {
"url": "https://storage.googleapis.com/falserverless/example_outputs/qwen3-tts/tts_out.mp3",
"channels": 1,
"file_name": "n5Ynr2aFKUPw1QjLYjB_4_XEdHoD1K.mp3",
"sample_rate": 24000,
"content_type": "audio/mpeg",
"duration": 13.025333333333334
}
}url string* requiredThe URL where the file can be downloaded from.
content_type stringThe mime type of the file.
file_name stringThe name of the file. It will be auto-generated if not provided.
file_size integerThe size of the file in bytes.
duration floatThe duration of the audio
channels integerThe number of channels in the audio
sample_rate integerThe sample rate of the audio