introduction

sync. introduces a simple yet powerful way to bring your text to life. our /speak endpoint utilizes state-of-the-art technology to transform any text into spoken words, offering a range of voices and languages to choose from. it’s designed for developers looking to add voice capabilities to their applications, making digital content more accessible and engaging.

discover how to seamlessly integrate spoken audio into your projects for narrations, voiceovers, interactive voice responses, and more. our api is built to be straightforward and developer-friendly, enabling you to start creating voice content in no time.

api features

natural-sounding voices

leverage our diverse set of high-quality, natural-sounding voices across various languages.

flexible integration

easily incorporate text-to-speech capabilities into your applications with minimal effort.

customization options

customize voice parameters to match your specific requirements, enhancing the listening experience.

available models

explore our diverse range of models, each designed for specific syncing needs. selecting the appropriate model ensures optimal performance and results.

model id:

sync-1.6.0

description: our best mode, everything good about sync-1.5 but now with fluid, human-like mouth movements. When to switch to 1.5: (i) you want the mouth movements to be more visibly prominent, (ii) you observe visual artifacts at the scene boundaries.

when to use: opt for this model to address nuances in teeth visibility and mouth coloration for a flawless finish.

model id:

sync-1.5.0

description: accurate, high-resolution lipsync that has been proven to be reliable over a large variety of videos. Why choose this: if sync-1.6 model gives you feeble-looking lip movements, this version can perform better.

why choose: perfect when upgrading from earlier versions or seeking a stable, tested option when the latest beta model doesn’t fit your project needs.

model id:

wav2lip++

description: low-resolution, fast, lipsync that will be free forever. Not suitable for commercial use.

why choose: use this for fast processing of low-resolution videos or for testing purposes.

model ids:

sync-1

sync-1.5.1-beta

description: offering compatibility for projects initiated on older standards, this model ensures continuity. automatically upgrades to sync-1.5.0 for enhanced outcomes.

legacy advantage: use this for ongoing projects needing legacy support with the benefit of automatic quality improvements.

built-in voices

Discover our selection of built-in voices available for the animate api, or create a custom voice by following the guide here.

quick start

authentication

before you can start using our api, you need to authenticate your requests. this is done using an x-api-key that links your requests to your account. if you don’t have an api key yet, check out the instructions here to obtain one.

create your speak request

translate your videos

now that you have an x-api-key, you can test out the /speak endpoint. to try out the speak endpoint via the playground above follow the instructions below:

authorize

enter your api key in the x-api-key field within the Authorization section.

enter your x-api-key in the authorization section

enter params

enter the params in the body section:

enter the video url, target language, and model in the body section

example input

{
  "transcript": "Hello, I hope you enjoy this audio!",
  "targetLanguage": "e5361405-4967-446d-ad63-2f6ed8729c66", # default male voice
}

submit

click the Send button to submit your speak request. after submission, you will receive a response that includes the id of your speak job, the current status, and details of the original submission.

understanding the response

the initial response provides you with essential details to track your job:

{
  "id": "unique_job_id",
  "createdAt": "date_time",
  "status": "processing",
  "step": "synthesizing",
  "audioUrl": "",
  "transcriptUrl": "https://example.com/audio.mp3",
  "voiceId": "e5361405-4967-446d-ad63-2f6ed8729c66",
  "creditsDeducted": 123,
  "webhookUrl": null,
  "errorMessage": null
}

your job’s status will start as pending and move to processing. use the returned id with the GET /speak/{id} endpoint to periodically poll for the status of your job. this polling is crucial for knowing when your video is ready.

polling for completion

periodically send requests to GET /speak/{id} with your job id. when the job status changes to completed, the response will include a URL to download your synced video.

Click here to view instructions on polling for job completion with the get translate api playground

Authorizations

x-api-key

string

headerrequired

Body

application/json

transcript

string

required

A string of text to be spoken by the AI

voiceId

string

default: e5361405-4967-446d-ad63-2f6ed8729c66required

The voice to use for audio generation

maxCredits

number

Maximum number of credits to use for audio generation. If job exceeds this value, the job will be aborted

webhookUrl

string

A url to send a notification to upon completion of audio generation

Response

201 - application/json

string

required

A unique identifier for the audio.

createdAt

string

required

The date and time the audio was created.

status

string

required

The status of the audio.

transcriptUrl

string

required

A URL to a file containing the input transcript.

voiceId

string

required

The voice ID used for the audio.

creditsDeducted

number

required

The number of credits deducted for the audio.

errorMessage

string

required

An error message if the audio failed to process.

step

string

The step of the audio.

audioUrl

string

A URL which can be used to download the audio.

webhookUrl

string

The webhook URL to notify the user when the audio is ready.

api documentation

lipsync

animate

speak

voices

Post speak

introduction

api features

natural-sounding voices

flexible integration

customization options

available models

built-in voices

quick start

authentication

create your speak request

translate your videos

example input

understanding the response

polling for completion

Authorizations

Body

Response

api documentation

lipsync

animate

speak

voices

​introduction

​api features

natural-sounding voices

flexible integration

customization options

​available models

​built-in voices

​quick start

​authentication

​create your speak request

​translate your videos

example input

understanding the response

polling for completion

Authorizations

Body

Response

introduction

api features

available models

built-in voices

quick start

authentication

create your speak request

translate your videos