latestOpenAPI 3.0.02026-07-248574216.0 KB

726b2a637ae8

Text2Audio

Text2Speech

The Text2Speech service helps generate an audio based on the text introduced as input by the user. The audio will speak the text provided.

post/text2speech

Request body

textstring required

The text to speak. Up to 5000 characters.

language'en' | 'fr'

The language to speak.

model'urn:air:openai:model:openai:tts-1@1' | 'urn:air:elevenlabs:model:elevenlabs:eleven-v3@1' | 'urn:air:async:model:async:async-flash-v1.0@1' nullable

Optionally choose a specific AI model to use for this audio generation. If not specified, a default model will be applied. Please note that the default model may change over time as Picsart continues to improve performance and accuracy. Any change to the default will be made only after thorough testing and validation to ensure it delivers better results. If you require consistent behavior or wish to evaluate different models on your own, we recommend explicitly setting this parameter.

voicestring nullable

Voice for speech synthesis. Considering different models have different voices and that list changes over time, the list of supported voices is not provided here. Please go ahead to check for available voices on each provider's website. When not provided, the following default voices will be applied:

OpenAI > alloy
Eevenlabs > Rachel
Async > nyomi

Response

Accepted.

status'success' | 'error' | 'processing'

inference_idstring nullable