Actions12
- Audio Actions
- Image Actions
- Storage Actions
- Text Actions
- Video Actions
Audio → Audio Generation
AI-generatedSummary
Generate speech from text via Pollinations TTS API and return audio binary with metadata
Inputs
- audioText (required) — Text to convert to speech
- audioModel — AI model to use for speech. Choose from the list, or specify an ID using an expression.
- voice — Voice to use for TTS. Choose from the list, or specify an ID using an expression.
- audioFormat — Audio output format. Options: AAC, FLAC, MP3, Opus, PCM, WAV. Default: mp3.
Output shape
paired item with json metadata and binary audio data
Return shape taken from source (executeAudioGeneration); properties used only for UI declaration
Examples
Example 1: Generate a short MP3 clip of spoken text
audioText: 'Hello world', audioFormat: 'mp3' (default), no model or voice specified (uses Pollinations defaults)