This endpoint retrieves recordings for a particular voice.


UUID of the voice to which the recording belongs

voice_uuid

page

page_size

This endpoint creates a recording for a particular voice.


{
    "file"

"text"

"riquired"

"emotion"

"is_active"

the recording is not used to train the voice model"

"name"

"fill"

the recording will be used for Resemble Fill."
    }

This endpoint retrieves one recording for a particular voice.


recording_uuid

This endpoint updates a recording for a particular voice.


Defaulted to false. If true, the recording will be used for Resemble Fill.

If false, the recording is not used to train the voice model

This endpoint deletes one recording for a particular voice.


Returns advanced voice information such as underlying model versions when set to true. 

advanced

This endpoint creates a voice and optionally starts training


A URL (webhook) that will be notified upon voice training completion Please see here for callback details

A base-64 encoded Wavefile string containing your consent and authorization to create and clone a voice. Please see the Voice Consent section for more details.

A URL to a dataset on which to train the voice on. Please see here for acceptable dataset formats

The type of voice to create. Either rapid or professional. If not provided defaults to professional

Returns advanced voice information such as underlying model versions when set to true.

voiceUuid

This endpoint builds a voice. The voice must have at least 30 active recordings. To upload recordings for a voice, see the documentation for the recording resource.


Defaulted to false. If true, the Resemble Fill model will be trained.

Submit an audio file for deepfake detection.


A URL to sent the results to when analysis is completed.

The URL of the audio file to be analyzed for deepfake detection. The audio file should be in WAV format. Provide a valid HTTPS URL pointing to the audio file.

Retrieve the deepfake detection result using the provided UUID.

Apply a watermark to an audio file using the provided URL.


The URL of the audio file to be watermarked. The audio file should be in WAV format. Provide a valid HTTPS URL pointing to the audio file.

Detect a watermark in an audio file using the provided URL.

This endpoint retrieves batches in a project.


Batches for the project with this UUID will be returned

project_uuid

This endpoint creates a batch in a project.


UUID of the project to which the clip should belong

An array of strings where each string is content to be synthesized (this can be raw text or ssml) or an array of arrays where each element in the nested array conforms to the shape of ['title', ssml']. Max size of each element in the batch is 3,000 characters excluding ssml tags. Max size of the array is 1,000.

The URL to POST the result of the batch to.

one of the following values: wav or mp3 The format of the generated audio

one of the following values: PCM_32, PCM_24, PCM_16, or MULAW  The audio bit depth of generated audio

one of the following values: 8000, 16000, 22050 or 44100 The sample rate (Hz) of the generated audio

UUID of the voice to use for synthesizing

This endpoint retrieves one batch in a project.


batch_uuid

UUID of the project to which the batch belongs

This endpoint deletes a batch and all associated clips in a project.


This endpoint retrieves clips in a project.


Clips for the project with this UUID will be returned

 Searches for clips with a title matching the value 

This endpoint retrieves one clip in a project.


clip_uuid

This endpoint updates a clip in a project.



Content to be synthesized. Max size of 3,000 characters excluding SSML tags.

 Whether to include timestamps for the generated content -- see the documentation on timestamps for more information

The sample rate (Hz) of the generated audio

This endpoint deletes a clip in a project.


This endpoint creates a clip in a project.


The URL to POST the final clip to. If provided, the request is considered 'asynchronous', otherwise it's considered 'syncronous'.

Whether to return raw audio data in the response.

Whether to apply substitutions and phonemes configured through the dashboard

This endpoint retrieves your user account.

This endpoint retrieves the teams associated with the user account.


phonemeUuid

Whether to allow collaboration features for this project

projectUuid

This endpoint retrieves term substitutions.

This endpoint creates a term substitution.

This endpoint retrieves a term substitution.

UUID of the term substitution to retrieve

substitutionUuid

This endpoint deletes a term substitution.

term_substitution_Uuid

Resemble AI

Resemble AIAPI

Resemble AI API

Pre-configured, Predictable, Single Interface, Ready-to-use, Opinionated & Managed API Explorer & Server. Bring your API credentials, configure and access your 3rd party APIs. Using LowCodeAPI securely manage all integrations in one place.