Picsart Generative AI-Hub icon

Picsart Generative AI-Hub

Generate and edit media with Picsart GenAI API: images, stickers, sound, video, and prompt-based image editing.

Actions7

Generate Speech from Prompt

AI-generated

Summary

Generates spoken audio from input text using the Picsart GenAI text-to-speech API.

Inputs

  • text2SpeechText (required) — The text to speak (up to 5000 characters).
  • text2SpeechLanguage — The language to speak (defaults to 'en').
  • text2SpeechModel — AI model for text-to-speech (defaults to OpenAI tts-1).
  • text2SpeechVoice — Optional voice name for synthesis; defaults to provider-specific defaults.

Output shape

One item per input item containing a binary audio file and metadata.

Audio is polled until ready (max 600 attempts). Returns an MP3 file named 'generated-speech.mp3'.

Examples

Example 1: Convert a static text string to audio in the English language.

Set text2SpeechText to 'Hello world' and leave other parameters at defaults.

Example 2: Generate speech in French with a specific provider model.

Set text2SpeechText to 'Bonjour', text2SpeechLanguage to 'fr', and text2SpeechModel to ElevenLabs.

Links

Discussion