OpenAgentSkill Registry Manifest
Skill: venice-audio-speech
Slug: veniceai-venice-audio-speech
Category: automation
Description: Generate speech from text via POST /audio/speech, and clone a voice via POST /audio/voices. Covers TTS models (Kokoro, Qwen 3, xAI, Inworld, Chatterbox, Orpheus, ElevenLabs Turbo, MiniMax, Gemini Flash, Gradium), voices per family, cloned-voice handles, output formats (mp3/opus/aac/flac/wav/pcm), streaming, prompt/emotion styling, temperature/top_p, and language hints.

Agent fit:
- Decision: 67/100 Prototype first
- Primary fit: Browser automation
- Role: Fallback candidate

Supply profile:
- Track: Coding and developer agents
- Scenario: GitHub automation
- Applicable agents: Claude Code, OpenAI Agents, Browser agents, CLI, Codex
- Maintenance: 6d since push
- Risk: Needs review

Trust:
- Trust score: 68/100 Manual review
- Audit: 75/100 Needs review

Attribution:
- Status: Registry indexed
- Source: github candidate review
- Creator: veniceai
- Claim URL: https://www.openagentskill.com/skills/veniceai-venice-audio-speech#claim-this-skill

Install:
npx skills add veniceai/skills --skill venice-audio-speech

URLs:
- Web: https://www.openagentskill.com/skills/veniceai-venice-audio-speech
- API: https://www.openagentskill.com/api/agent/skills/veniceai-venice-audio-speech
- Install API: https://www.openagentskill.com/api/skills/veniceai-venice-audio-speech/install
- Repository: https://github.com/veniceai/skills/tree/main/skills/venice-audio-speech