API reference

Audio

POSThttps://api.oneover.com/functions/v1/api-v1-audioScope: audio

Generate speech or music. Synchronous — returns a hosted audio URL when ready.

Request body

Parameters

Name	Type	Required	Description
`model`	`string`	Yes	Speech or music model ID (OpenAI TTS, Gemini TTS, Grok TTS, Lyria, etc.).
`prompt`	`string`	Yes	Text to speak, or music description.
`audio_kind`	`string`	No	speech (default) or music.
`voice`	`string`	No	Voice id for speech models.
`speakers`	`array`	No	Two-speaker dialogue for Gemini TTS: [{ name, voice }, ...].
`speed`	`number`	No	Speech speed multiplier where supported.
`duration_seconds`	`number`	No	Music length (seconds).
`music_style`	`string`	No	vocals, instrumental, or any.

Examples

Request

curl -X POST "https://api.oneover.com/functions/v1/api-v1-audio" \
  -H "Authorization: Bearer oo_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini-tts",
    "prompt": "Welcome to OneOver.",
    "audio_kind": "speech",
    "voice": "alloy"
  }'

Response

200 OK

{
  "request_id": "uuid",
  "model": "gpt-4o-mini-tts",
  "audio_kind": "speech",
  "audio_url": "https://...",
  "credits_charged": 2,
  "balance": { "subscription": 14992, "anytime": 5000 }
}

See also Models for available speech and music model IDs on your org plan.