Leina 
Wanta 
Generate a Narration
Choose a language-appropriate voice and synthesize supplied narration text.
/oo AiVOOV: List AiVOOV voices for [language code]. Use voice [chosen voice ID] to speak this narration: [narration text].
Connect AiVOOV to Your AI Agent
Select a voice for your text, or assign different voices to dialogue segments before generating audio.
2 tools API key
Try a AiVOOV Task
Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.
oo Skill AiVOOV
Render a Multi-Voice Dialogue
Assign voice IDs to ordered dialogue segments and render them into an audio payload.
/oo AiVOOV: Generate AiVOOV audio for these dialogue segments in order: [voice ID and text for each segment]. Use default voice settings.
Start Working with AiVOOV
-
Install OOMOL
Set up oo CLI and the oo Skill in your agent.
Install OOMOL → -
Connect AiVOOV
Connect your AiVOOV API key.
Connect AiVOOV → -
Give Your Agent a Task
Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →
Choose Your Agent
- An AiVOOV API key and text to synthesize.
- Each text segment needs a voice ID. Your AI product must be able to decode the audio data to provide playback or a file.
AiVOOV Tools
AiVOOV exposes voice selection and text-to-speech generation through this integration. Audio is returned as encoded data.
Voice Selection
List voices, optionally filtered by language.
Speech Generation
Synthesize one or more text segments with selected voices and voice controls.
2 tools
List Voices
List available AiVOOV voices, optionally filtered by language code.
aivoov.list_voices Create Audio
Generate base64 audio from one or more voice/text segments.
aivoov.create_audio No matching tools.
Frequently Asked Questions
How do I choose a voice?
List voices for the language you need, then select a voice ID for each text segment.
Will the operation return a download link?
It returns encoded audio data. Playback or saving a file depends on your AI product’s ability to decode that data.
Can I adjust speech delivery?
The input supports pitch, speaking rate, and volume adjustments for each segment. You can also request the default settings.