Rendley docs

AI audio & voice

Text-to-speech, music generation, sound effects, voice isolation, and voice changing. All audio generation is asynchronous — you start a job and poll until it completes.

Call this endpoint to discover every action, its available models, and the JSON schema each model accepts for params. Use the schema from the response to build your params object in step 2.

Step 2 is the specific generation endpoint below. Pick the one you need, pass project_id, optionally model_id, and the params from the schema above.

#Generate music

POST/v1/ai/generate-music

Enqueue a job to generate music from a text prompt describing genre, instruments, tempo, and structure.

Request body

model_idstringOptional

Which model to use. Call GET /ai/tools to see available models. Each action has a default.

paramsjsonRequired

Model-specific parameters. Call GET /ai/tools to get the schema for each model.

project_idstringRequired
Response codes
200

OK

400

Bad Request

401

Unauthorized

402

Payment Required

#Calculate music generation cost

POST/v1/ai/generate-music/cost

Calculate the credit cost of generating music from a text prompt.

Request body

model_idstringOptional
paramsobjectOptional
project_idstringRequired
Response codes
200

OK

400

Bad Request

401

Unauthorized

#Generate a sound effect

POST/v1/ai/generate-sound-effect

Enqueue a job to generate a custom sound effect from a text description.

Request body

model_idstringOptional

Which model to use. Call GET /ai/tools to see available models. Each action has a default.

paramsjsonRequired

Model-specific parameters. Call GET /ai/tools to get the schema for each model.

project_idstringRequired
Response codes
200

OK

400

Bad Request

401

Unauthorized

402

Payment Required

#Calculate sound effect generation cost

POST/v1/ai/generate-sound-effect/cost

Calculate the credit cost of generating a sound effect from a text description.

Request body

model_idstringOptional
paramsobjectOptional
project_idstringRequired
Response codes
200

OK

400

Bad Request

401

Unauthorized

#Generate text-to-speech audio

POST/v1/ai/text-to-speech

Enqueue a job to generate spoken-word audio from text using a selected voice.

Request body

model_idstringOptional

Which model to use. Call GET /ai/tools to see available models. Each action has a default.

paramsjsonRequired

Model-specific parameters. Call GET /ai/tools to get the schema for each model.

project_idstringRequired
Response codes
200

OK

400

Bad Request

401

Unauthorized

402

Payment Required

#Calculate text-to-speech cost

POST/v1/ai/text-to-speech/cost

Calculate the credit cost of generating spoken-word audio from text.

Request body

model_idstringOptional
paramsobjectOptional
project_idstringRequired
Response codes
200

OK

400

Bad Request

401

Unauthorized

#List text-to-speech voices

GET/v1/ai/text-to-speech/voices

List available text-to-speech voices, with optional pagination and search.

Query parameters

pagestringOptional

Page number

limitstringOptional

Page size

querystringOptional

Search query

Response codes
200

OK

401

Unauthorized

#Get a voice preview

GET/v1/ai/text-to-speech/voices/{voiceId}/preview

Get a preview audio URL for a specific text-to-speech voice.

Path parameters

voiceIdstring

Voice ID

Response codes
200

OK

401

Unauthorized

#Change the voice in a clip

POST/v1/ai/voice-changer

Enqueue a job to replace the voice in an audio or video clip with a different target voice.

Request body

clip_idstringOptional
file_urlstringOptional
model_idstringOptional

Which model to use. Call GET /ai/tools to see available models. Each action has a default.

paramsjsonRequired

Model-specific parameters. Call GET /ai/tools to get the schema for each model.

project_idstringRequired
Response codes
200

OK

400

Bad Request

401

Unauthorized

402

Payment Required

#Calculate voice changer cost

POST/v1/ai/voice-changer/cost

Calculate the credit cost of replacing the voice in an audio or video clip.

Request body

clip_idstringOptional
file_urlstringOptional
model_idstringOptional
paramsobjectOptional
project_idstringRequired
Response codes
200

OK

400

Bad Request

401

Unauthorized

#Isolate voice from audio

POST/v1/ai/voice-isolation

Enqueue a job to isolate human voice and remove background noise, music, and other unwanted sounds.

Request body

clip_idstringOptional
file_urlstringOptional
model_idstringOptional

Which model to use. Call GET /ai/tools to see available models. Each action has a default.

paramsjsonRequired

Model-specific parameters. Call GET /ai/tools to get the schema for each model.

project_idstringRequired
Response codes
200

OK

400

Bad Request

401

Unauthorized

402

Payment Required

#Calculate voice isolation cost

POST/v1/ai/voice-isolation/cost

Calculate the credit cost of isolating voice and removing background noise from audio.

Request body

clip_idstringOptional
file_urlstringOptional
model_idstringOptional
paramsobjectOptional
project_idstringRequired
Response codes
200

OK

400

Bad Request

401

Unauthorized

#Step 3: Poll the job

GET/v1/jobs/{job_id}

Poll this endpoint every few seconds until status is completed or failed. See Jobs and polling for the full loop.

The result contains a media_id and file_hash. Use the next step to get a download URL.

Pass the file_hash from the completed job to get a presigned download URL. The storage_url is time-limited, so download the file promptly.