cleya tts
Generate a voiceover clip from text via the OpenAI audio API (opt-in cloud; needs OPENAI_API_KEY)
Cost: network — OpenAI audio API (OPENAI_API_KEY)
cleya tts --text "Welcome to the show" --voice nova --output vo.mp3
Options
| Flag | What it does | |
|---|---|---|
--text | The text to speak | required · string |
--voice | Voice (alloy, echo, fable, onyx, nova, shimmer, …); default alloy | string |
--model | TTS model (default gpt-4o-mini-tts) | string |
--format | Audio format: mp3 (default), wav, opus, aac, flac | string |
--speed | Speed 0.25–4.0 (default 1.0) | string |
--instructions | Steer delivery — tone/energy/pacing (e.g. 'Upbeat, warm, confident; punchy; not flat') | string |
--tone | Preset delivery instructions (shortcut for --instructions) | string · one of energetic, warm, calm, serious, excited |
--output | Output audio path | string |
--overwrite | Overwrite output file if it exists | boolean |
Category: author — create media from specs (scene DSL, cards, titles, captions, voiceover, capture)
Generated from the toolkit
Generated from cleya capabilities, the toolkit's own manifest, so it cannot drift.
Run cleya tts --help for the same information in your terminal.