Audio / Speech API

TTS (text-to-speech), sound effects and audio isolation via ElevenLabs. Natural narration in 29 languages, including Turkish. (For speech-to-text, use /v1/chat/completions with input_audio and openai/gpt-audio or google/gemini-2.5-flash.)

bolt

This page is the audio part of the Content Generation API.

All generation endpoints (video, image, audio, voice, music) use the same backend. /v1/audio/generate and /v1/voice/generate are semantic aliases for audio models — for the full voice list, parameters and details, see video-api → Audio Models.

Audio Generation (TTS)

POST /v1/voice/generate

Generates speech from text (asynchronous). Equivalent: POST /v1/audio/generate or POST /v1/video/generate.

Quick Example (Turkish TTS, Rachel)

cURL

curl -X POST https://api.onysoft.com/v1/voice/generate \
  -H "Authorization: Bearer sk-ony-YOUR-KEY" \
  -d '{
    "model": "elevenlabs/text-to-speech-multilingual-v2",
    "prompt": "Merhaba, ben Rachel. Onysoft AI üzerinden konuşuyorum.",
    "voice": "Rachel"
  }'
            

Supported Voices (case-sensitive)

Female: Rachel (default), Alice, Aria, Charlotte, Jessica, Laura, Lily, Matilda, Sarah
Male: Brian, Bill, Callum, Charlie, Chris, Daniel, Eric, George, Liam, Roger, Will

warning

The voice value is case-sensitive

If you send "rachel" or "RACHEL", KieAI returns a 500 "This voice is not within the range of allowed options" error. Capitalize the first letter. A name outside the list gives the same error.

Sound Effect

cURL

curl -X POST https://api.onysoft.com/v1/audio/generate \
  -H "Authorization: Bearer sk-ony-YOUR-KEY" \
  -d '{
    "model": "elevenlabs-sound-effect-v2",
    "prompt": "thunder rolling in distant mountains, heavy rain",
    "duration_seconds": 8.0,
    "prompt_influence": 0.5
  }'
            

Audio Models

Model	Type	Price (USD)
`elevenlabs/text-to-speech-multilingual-v2`	Multilingual TTS ⭐	$0.090
`elevenlabs/text-to-speech-turbo-2-5`	Low-latency TTS*	$0.045
`elevenlabs-v3-text-to-dialogue`	Multi-character dialogue	$0.105
`elevenlabs-sound-effect-v2`	Sound effect generation*	$0.002
`elevenlabs-audio-isolation`	Vocal/instrument isolation	$0.002

* turbo-2-5 and sound-effect-v2 are currently having a temporary "internal error" on the provider side. multilingual-v2 is recommended.

Status Lookup

cURL

curl https://api.onysoft.com/v1/audio/status/vtask_xyz789 \
  -H "Authorization: Bearer sk-ony-YOUR-KEY"
            

For all parameters (stability, similarity_boost, style) and TTS documentation, see video-api → Audio Models.