Run models all in one Sandbox 🏖️
Docs
Log-inSign-up

fal-ai/tada/3b/text-to-speech

A unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment.
Inference
Commercial use
Schema
LLMs
PlaygroundAPI

Table of contents

About

Generate 3B

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

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/tada/3b/text-to-speech", {
  input: {
    audio_url: "https://storage.googleapis.com/falserverless/example_inputs/reference_audio.wav",
    prompt: "The autumn leaves danced gracefully through the crisp morning air, painting the cobblestone streets with shades of amber and gold."
  },
  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);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.
import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

3. Queue#

Submit a request#

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/tada/3b/text-to-speech", {
  input: {
    audio_url: "https://storage.googleapis.com/falserverless/example_inputs/reference_audio.wav",
    prompt: "The autumn leaves danced gracefully through the crisp morning air, painting the cobblestone streets with shades of amber and gold."
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

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/tada/3b/text-to-speech", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

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/tada/3b/text-to-speech", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

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.

Data URI (base64)#

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.

Hosted files (URL)#

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.

Uploading files#

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);

Read more about file handling in our file upload guide.

5. Schema#

Input#

audio_url string* required

URL of the reference audio file for voice cloning. The model will replicate this speaker's voice characteristics.

transcript string

Transcript of the reference audio. For non-English audio, providing a transcript is required since the built-in ASR is English-only. Default value: ""

prompt string* required

The text to synthesize into speech using the reference speaker's voice.

language LanguageEnum

Language for text alignment. Use the appropriate code for non-English synthesis. Default value: "en"

Possible enum values: en, ar, ch, de, es, fr, it, ja, pl, pt

num_extra_steps integer

Number of extra autoregressive steps for speech continuation beyond the input text. Useful for generating trailing prosody or silence.

temperature float

Sampling temperature for text token generation. Higher values produce more varied output. Default value: 0.6

top_p float

Top-p (nucleus) sampling parameter for text generation. Default value: 0.9

repetition_penalty float

Penalty applied to repeated tokens during generation. Default value: 1.1

acoustic_cfg_scale float

Classifier-free guidance scale for acoustic feature generation. Default value: 1.6

noise_temperature float

Temperature for noise in the flow matching diffusion process. Default value: 0.9

num_inference_steps integer

Number of ODE solver steps for flow matching acoustic generation. More steps improve quality at the cost of speed. Default value: 20

speed_up_factor float

Factor to speed up or slow down the generated speech. Values > 1.0 speed up, < 1.0 slow down. Default value: 1

output_format OutputFormatEnum

The format of the output audio file. Default value: "wav"

Possible enum values: wav, mp3

{
  "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/reference_audio.wav",
  "transcript": "Some call me nature, others call me mother nature.",
  "prompt": "The autumn leaves danced gracefully through the crisp morning air, painting the cobblestone streets with shades of amber and gold.",
  "language": "en",
  "temperature": 0.6,
  "top_p": 0.9,
  "repetition_penalty": 1.1,
  "acoustic_cfg_scale": 1.6,
  "noise_temperature": 0.9,
  "num_inference_steps": 20,
  "speed_up_factor": 1,
  "output_format": "wav"
}

Output#

audio AudioFile* required

The generated speech audio file.

{
  "audio": {
    "url": "https://v3b.fal.media/files/b/0a91e54b/Ldhq_0EWjUdnUEwn-Tcrk_nfs9DTGI.wav"
  }
}

Other types#

AudioFile#

url string* required

The URL where the file can be downloaded from.

content_type string

The mime type of the file.

file_name string

The name of the file. It will be auto-generated if not provided.

file_size integer

The size of the file in bytes.

duration float

The duration of the audio

channels integer

The number of channels in the audio

sample_rate integer

The sample rate of the audio

bitrate string | integer

The bitrate of the audio (e.g., '192k' or 192000)

Related Models