{
  "schemaVersion": "1.0",
  "item": {
    "slug": "venice-ai",
    "name": "Venice AI",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/jonisjongithub/venice-ai",
    "canonicalUrl": "https://clawhub.ai/jonisjongithub/venice-ai",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/venice-ai",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=venice-ai",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/api.md",
      "scripts/venice-edit.py",
      "scripts/venice-image.py",
      "scripts/venice-upscale.py",
      "scripts/venice-video.py"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/venice-ai"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/venice-ai",
    "agentPageUrl": "https://openagent3.xyz/skills/venice-ai/agent",
    "manifestUrl": "https://openagent3.xyz/skills/venice-ai/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/venice-ai/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "What is Venice AI?",
        "body": "Venice AI is the AI platform for people who don't want Big Tech watching over their shoulder. Unlike OpenAI, Anthropic, and Google — where every prompt is logged, analyzed, and potentially used to train future models — Venice offers true privacy with zero data retention on private models. Your conversations stay yours.\n\nVenice is also uncensored: no content filters, no refusals, no \"I can't help with that.\" The AI answers what you actually ask, whether that's creative fiction, security research, controversial topics, or anything else mainstream AI platforms won't touch.\n\nWhy agents should care:\n\nPrivate inference — Models marked \"Private\" have zero data retention. Process sensitive data without it leaking into training sets.\nUncensored responses — No guardrails blocking legitimate use cases. Generate any content your workflow needs.\nOpenAI-compatible API — Drop-in replacement. Same API format, just change the base URL.\n30+ models — From tiny efficient models to Claude Opus 4.5, GPT-5.2, and Venice's own uncensored models.\nBuilt-in web search — LLMs can search the web and cite sources in a single API call.\nImage & video generation — Flux, Sora, Runway, WAN models for visual content.\n\nThis skill gives you the complete Venice platform: text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing.\n\n⚠️ API changes: If something doesn't work as expected, check docs.venice.ai — the API specs may have been updated since this skill was written."
      },
      {
        "title": "Prerequisites",
        "body": "Python 3.10+\nVenice API key (free tier available at venice.ai/settings/api)"
      },
      {
        "title": "Get Your API Key",
        "body": "Create account at venice.ai\nGo to venice.ai/settings/api\nClick \"Create API Key\" → copy the key (starts with vn_...)"
      },
      {
        "title": "Configure",
        "body": "Option A: Environment variable\n\nexport VENICE_API_KEY=\"vn_your_key_here\"\n\nOption B: Clawdbot config (recommended)\n\n// ~/.clawdbot/clawdbot.json\n{\n  skills: {\n    entries: {\n      \"venice-ai\": {\n        env: { VENICE_API_KEY: \"vn_your_key_here\" }\n      }\n    }\n  }\n}"
      },
      {
        "title": "Verify",
        "body": "python3 {baseDir}/scripts/venice.py models --type text"
      },
      {
        "title": "Scripts Overview",
        "body": "ScriptPurposevenice.pyText generation, models, embeddings, TTS, transcriptionvenice-image.pyImage generation (Flux, etc.)venice-video.pyVideo generation (Sora, WAN, Runway)venice-upscale.pyImage upscalingvenice-edit.pyAI image editing"
      },
      {
        "title": "Model Discovery & Selection",
        "body": "Venice has a huge model catalog spanning text, image, video, audio, and embeddings."
      },
      {
        "title": "Browse Models",
        "body": "# List all text models\npython3 {baseDir}/scripts/venice.py models --type text\n\n# List image models\npython3 {baseDir}/scripts/venice.py models --type image\n\n# List all model types\npython3 {baseDir}/scripts/venice.py models --type text,image,video,audio,embedding\n\n# Get details on a specific model\npython3 {baseDir}/scripts/venice.py models --filter llama"
      },
      {
        "title": "Model Selection Guide",
        "body": "NeedRecommended ModelWhyCheapest textqwen3-4b ($0.05/M in)Tiny, fast, efficientBest uncensoredvenice-uncensored ($0.20/M in)Venice's own uncensored modelBest private + smartdeepseek-v3.2 ($0.40/M in)Great reasoning, efficientVision/multimodalqwen3-vl-235b-a22b ($0.25/M in)Sees imagesBest codingqwen3-coder-480b-a35b-instruct ($0.75/M in)Massive coder modelFrontier (budget)grok-41-fast ($0.50/M in)Fast, 262K contextFrontier (max quality)claude-opus-4-6 ($6/M in)Best overall qualityReasoningkimi-k2-5 ($0.75/M in)Strong chain-of-thoughtWeb searchAny model + enable_web_searchBuilt-in web search"
      },
      {
        "title": "Basic Generation",
        "body": "# Simple prompt\npython3 {baseDir}/scripts/venice.py chat \"What is the meaning of life?\"\n\n# Choose a model\npython3 {baseDir}/scripts/venice.py chat \"Explain quantum computing\" --model deepseek-v3.2\n\n# System prompt\npython3 {baseDir}/scripts/venice.py chat \"Review this code\" --system \"You are a senior engineer.\"\n\n# Read from stdin\necho \"Summarize this\" | python3 {baseDir}/scripts/venice.py chat --model qwen3-4b\n\n# Stream output\npython3 {baseDir}/scripts/venice.py chat \"Write a story\" --stream"
      },
      {
        "title": "Web Search Integration",
        "body": "# Auto web search (model decides when to search)\npython3 {baseDir}/scripts/venice.py chat \"What happened in tech news today?\" --web-search auto\n\n# Force web search with citations\npython3 {baseDir}/scripts/venice.py chat \"Current Bitcoin price\" --web-search on --web-citations\n\n# Web scraping (extracts content from URLs in prompt)\npython3 {baseDir}/scripts/venice.py chat \"Summarize: https://example.com/article\" --web-scrape"
      },
      {
        "title": "Uncensored Mode",
        "body": "# Use Venice's own uncensored model\npython3 {baseDir}/scripts/venice.py chat \"Your question\" --model venice-uncensored\n\n# Disable Venice system prompts for raw model output\npython3 {baseDir}/scripts/venice.py chat \"Your prompt\" --no-venice-system-prompt"
      },
      {
        "title": "Reasoning Models",
        "body": "# Use a reasoning model with effort control\npython3 {baseDir}/scripts/venice.py chat \"Solve this math problem...\" --model kimi-k2-5 --reasoning-effort high\n\n# Strip thinking from output\npython3 {baseDir}/scripts/venice.py chat \"Debug this code\" --model qwen3-4b --strip-thinking"
      },
      {
        "title": "Advanced Options",
        "body": "# Temperature and token control\npython3 {baseDir}/scripts/venice.py chat \"Be creative\" --temperature 1.2 --max-tokens 4000\n\n# JSON output mode\npython3 {baseDir}/scripts/venice.py chat \"List 5 colors as JSON\" --json\n\n# Prompt caching (for repeated context)\npython3 {baseDir}/scripts/venice.py chat \"Question\" --cache-key my-session-123\n\n# Show usage stats\npython3 {baseDir}/scripts/venice.py chat \"Hello\" --show-usage"
      },
      {
        "title": "Embeddings",
        "body": "Generate vector embeddings for semantic search, RAG, and recommendations:\n\n# Single text\npython3 {baseDir}/scripts/venice.py embed \"Venice is a private AI platform\"\n\n# Multiple texts (batch)\npython3 {baseDir}/scripts/venice.py embed \"first text\" \"second text\" \"third text\"\n\n# From file (one text per line)\npython3 {baseDir}/scripts/venice.py embed --file texts.txt\n\n# Output as JSON\npython3 {baseDir}/scripts/venice.py embed \"some text\" --output json\n\nModel: text-embedding-bge-m3 (private, $0.15/M tokens)"
      },
      {
        "title": "Text-to-Speech (TTS)",
        "body": "Convert text to speech with 60+ multilingual voices:\n\n# Default voice\npython3 {baseDir}/scripts/venice.py tts \"Hello, welcome to Venice AI\"\n\n# Choose a voice\npython3 {baseDir}/scripts/venice.py tts \"Exciting news!\" --voice af_nova\n\n# List available voices\npython3 {baseDir}/scripts/venice.py tts --list-voices\n\n# Custom output path\npython3 {baseDir}/scripts/venice.py tts \"Some text\" --output /tmp/speech.mp3\n\n# Adjust speed\npython3 {baseDir}/scripts/venice.py tts \"Speaking slowly\" --speed 0.8\n\nPopular voices: af_sky, af_nova, am_liam, bf_emma, zf_xiaobei (Chinese), jm_kumo (Japanese)\n\nModel: tts-kokoro (private, $3.50/M characters)"
      },
      {
        "title": "Speech-to-Text (Transcription)",
        "body": "Transcribe audio files to text:\n\n# Transcribe a file\npython3 {baseDir}/scripts/venice.py transcribe audio.wav\n\n# With timestamps\npython3 {baseDir}/scripts/venice.py transcribe recording.mp3 --timestamps\n\n# From URL\npython3 {baseDir}/scripts/venice.py transcribe --url https://example.com/audio.wav\n\nSupported formats: WAV, FLAC, MP3, M4A, AAC, MP4\n\nModel: nvidia/parakeet-tdt-0.6b-v3 (private, $0.0001/audio second)"
      },
      {
        "title": "Check Balance",
        "body": "python3 {baseDir}/scripts/venice.py balance"
      },
      {
        "title": "Pricing Overview",
        "body": "FeatureCostImage generation~$0.01-0.03 per imageImage upscale~$0.02-0.04Image edit$0.04Video (WAN)~$0.10-0.50Video (Sora)~$0.50-2.00Video (Runway)~$0.20-1.00\n\nUse --quote with video commands to check pricing before generation."
      },
      {
        "title": "Image Generation",
        "body": "# Basic generation\npython3 {baseDir}/scripts/venice-image.py --prompt \"a serene canal in Venice at sunset\"\n\n# Multiple images\npython3 {baseDir}/scripts/venice-image.py --prompt \"cyberpunk city\" --count 4\n\n# Custom dimensions\npython3 {baseDir}/scripts/venice-image.py --prompt \"portrait\" --width 768 --height 1024\n\n# List available models and styles\npython3 {baseDir}/scripts/venice-image.py --list-models\npython3 {baseDir}/scripts/venice-image.py --list-styles\n\n# Use specific model and style\npython3 {baseDir}/scripts/venice-image.py --prompt \"fantasy\" --model flux-2-pro --style-preset \"Cinematic\"\n\n# Reproducible results with seed\npython3 {baseDir}/scripts/venice-image.py --prompt \"abstract\" --seed 12345\n\nKey flags: --prompt, --model (default: flux-2-max), --count, --width, --height, --format (webp/png/jpeg), --resolution (1K/2K/4K), --aspect-ratio, --negative-prompt, --style-preset, --cfg-scale (0-20), --seed, --safe-mode, --hide-watermark, --embed-exif"
      },
      {
        "title": "Image Upscale",
        "body": "# 2x upscale\npython3 {baseDir}/scripts/venice-upscale.py photo.jpg --scale 2\n\n# 4x with AI enhancement\npython3 {baseDir}/scripts/venice-upscale.py photo.jpg --scale 4 --enhance\n\n# Enhanced with custom prompt\npython3 {baseDir}/scripts/venice-upscale.py photo.jpg --enhance --enhance-prompt \"sharpen details\"\n\n# From URL\npython3 {baseDir}/scripts/venice-upscale.py --url \"https://example.com/image.jpg\" --scale 2\n\nKey flags: --scale (1-4, default: 2), --enhance (AI enhancement), --enhance-prompt, --enhance-creativity (0.0-1.0), --url, --output"
      },
      {
        "title": "Image Edit",
        "body": "AI-powered image editing:\n\n# Add elements\npython3 {baseDir}/scripts/venice-edit.py photo.jpg --prompt \"add sunglasses\"\n\n# Modify scene\npython3 {baseDir}/scripts/venice-edit.py photo.jpg --prompt \"change the sky to sunset\"\n\n# Remove objects\npython3 {baseDir}/scripts/venice-edit.py photo.jpg --prompt \"remove the person in background\"\n\n# From URL\npython3 {baseDir}/scripts/venice-edit.py --url \"https://example.com/image.jpg\" --prompt \"colorize\"\n\nNote: The edit endpoint uses Qwen-Image which has some content restrictions."
      },
      {
        "title": "Video Generation",
        "body": "# Get price quote first\npython3 {baseDir}/scripts/venice-video.py --quote --model wan-2.6-image-to-video --duration 10s\n\n# Image-to-video (WAN - default)\npython3 {baseDir}/scripts/venice-video.py --image photo.jpg --prompt \"camera pans slowly\" --duration 10s\n\n# Image-to-video (Sora)\npython3 {baseDir}/scripts/venice-video.py --image photo.jpg --prompt \"cinematic\" \\\n  --model sora-2-image-to-video --duration 8s --aspect-ratio 16:9 --skip-audio-param\n\n# Video-to-video (Runway Gen4)\npython3 {baseDir}/scripts/venice-video.py --video input.mp4 --prompt \"anime style\" \\\n  --model runway-gen4-turbo-v2v\n\n# List models with available durations\npython3 {baseDir}/scripts/venice-video.py --list-models\n\nKey flags: --image or --video, --prompt, --model (default: wan-2.6-image-to-video), --duration, --resolution (480p/720p/1080p), --aspect-ratio, --audio/--no-audio, --quote, --timeout\n\nModels:\n\nWAN — Image-to-video, configurable audio, 5s-21s\nSora — Requires --aspect-ratio, use --skip-audio-param\nRunway — Video-to-video transformation"
      },
      {
        "title": "🔍 Web Search + LLM = Research Assistant",
        "body": "Use --web-search on --web-citations to build a research workflow. Venice searches the web, synthesizes results, and cites sources — all in one API call."
      },
      {
        "title": "🔓 Uncensored Creative Content",
        "body": "Venice's uncensored models work for both text AND images. No guardrails blocking legitimate creative use cases."
      },
      {
        "title": "🎯 Prompt Caching for Agents",
        "body": "If you're running an agent loop that sends the same system prompt repeatedly, use --cache-key to get up to 90% cost savings."
      },
      {
        "title": "🎤 Audio Pipeline",
        "body": "Combine TTS and transcription: generate spoken content with tts, process audio with transcribe. Both are private inference."
      },
      {
        "title": "🎬 Video Workflow",
        "body": "Generate or find a base image\nUse --quote to estimate video cost\nGenerate with appropriate duration/model\nVideos take 1-5 minutes depending on settings"
      },
      {
        "title": "Troubleshooting",
        "body": "ProblemSolutionVENICE_API_KEY not setSet env var or configure in ~/.clawdbot/clawdbot.jsonInvalid API keyVerify at venice.ai/settings/apiModel not foundRun --list-models to see available; use --no-validate for new modelsRate limitedCheck --show-usage outputVideo stuckVideos can take 1-5 min; use --timeout 600 for long ones"
      },
      {
        "title": "Resources",
        "body": "API Docs: docs.venice.ai\nStatus: veniceai-status.com\nDiscord: discord.gg/askvenice"
      }
    ],
    "body": "Venice AI — Complete Platform Skill\nWhat is Venice AI?\n\nVenice AI is the AI platform for people who don't want Big Tech watching over their shoulder. Unlike OpenAI, Anthropic, and Google — where every prompt is logged, analyzed, and potentially used to train future models — Venice offers true privacy with zero data retention on private models. Your conversations stay yours.\n\nVenice is also uncensored: no content filters, no refusals, no \"I can't help with that.\" The AI answers what you actually ask, whether that's creative fiction, security research, controversial topics, or anything else mainstream AI platforms won't touch.\n\nWhy agents should care:\n\nPrivate inference — Models marked \"Private\" have zero data retention. Process sensitive data without it leaking into training sets.\nUncensored responses — No guardrails blocking legitimate use cases. Generate any content your workflow needs.\nOpenAI-compatible API — Drop-in replacement. Same API format, just change the base URL.\n30+ models — From tiny efficient models to Claude Opus 4.5, GPT-5.2, and Venice's own uncensored models.\nBuilt-in web search — LLMs can search the web and cite sources in a single API call.\nImage & video generation — Flux, Sora, Runway, WAN models for visual content.\n\nThis skill gives you the complete Venice platform: text generation, web search, embeddings, TTS, speech-to-text, image generation, video creation, upscaling, and AI editing.\n\n⚠️ API changes: If something doesn't work as expected, check docs.venice.ai — the API specs may have been updated since this skill was written.\n\nPrerequisites\nPython 3.10+\nVenice API key (free tier available at venice.ai/settings/api)\nSetup\nGet Your API Key\nCreate account at venice.ai\nGo to venice.ai/settings/api\nClick \"Create API Key\" → copy the key (starts with vn_...)\nConfigure\n\nOption A: Environment variable\n\nexport VENICE_API_KEY=\"vn_your_key_here\"\n\n\nOption B: Clawdbot config (recommended)\n\n// ~/.clawdbot/clawdbot.json\n{\n  skills: {\n    entries: {\n      \"venice-ai\": {\n        env: { VENICE_API_KEY: \"vn_your_key_here\" }\n      }\n    }\n  }\n}\n\nVerify\npython3 {baseDir}/scripts/venice.py models --type text\n\nScripts Overview\nScript\tPurpose\nvenice.py\tText generation, models, embeddings, TTS, transcription\nvenice-image.py\tImage generation (Flux, etc.)\nvenice-video.py\tVideo generation (Sora, WAN, Runway)\nvenice-upscale.py\tImage upscaling\nvenice-edit.py\tAI image editing\nPart 1: Text & Audio\nModel Discovery & Selection\n\nVenice has a huge model catalog spanning text, image, video, audio, and embeddings.\n\nBrowse Models\n# List all text models\npython3 {baseDir}/scripts/venice.py models --type text\n\n# List image models\npython3 {baseDir}/scripts/venice.py models --type image\n\n# List all model types\npython3 {baseDir}/scripts/venice.py models --type text,image,video,audio,embedding\n\n# Get details on a specific model\npython3 {baseDir}/scripts/venice.py models --filter llama\n\nModel Selection Guide\nNeed\tRecommended Model\tWhy\nCheapest text\tqwen3-4b ($0.05/M in)\tTiny, fast, efficient\nBest uncensored\tvenice-uncensored ($0.20/M in)\tVenice's own uncensored model\nBest private + smart\tdeepseek-v3.2 ($0.40/M in)\tGreat reasoning, efficient\nVision/multimodal\tqwen3-vl-235b-a22b ($0.25/M in)\tSees images\nBest coding\tqwen3-coder-480b-a35b-instruct ($0.75/M in)\tMassive coder model\nFrontier (budget)\tgrok-41-fast ($0.50/M in)\tFast, 262K context\nFrontier (max quality)\tclaude-opus-4-6 ($6/M in)\tBest overall quality\nReasoning\tkimi-k2-5 ($0.75/M in)\tStrong chain-of-thought\nWeb search\tAny model + enable_web_search\tBuilt-in web search\nText Generation (Chat Completions)\nBasic Generation\n# Simple prompt\npython3 {baseDir}/scripts/venice.py chat \"What is the meaning of life?\"\n\n# Choose a model\npython3 {baseDir}/scripts/venice.py chat \"Explain quantum computing\" --model deepseek-v3.2\n\n# System prompt\npython3 {baseDir}/scripts/venice.py chat \"Review this code\" --system \"You are a senior engineer.\"\n\n# Read from stdin\necho \"Summarize this\" | python3 {baseDir}/scripts/venice.py chat --model qwen3-4b\n\n# Stream output\npython3 {baseDir}/scripts/venice.py chat \"Write a story\" --stream\n\nWeb Search Integration\n# Auto web search (model decides when to search)\npython3 {baseDir}/scripts/venice.py chat \"What happened in tech news today?\" --web-search auto\n\n# Force web search with citations\npython3 {baseDir}/scripts/venice.py chat \"Current Bitcoin price\" --web-search on --web-citations\n\n# Web scraping (extracts content from URLs in prompt)\npython3 {baseDir}/scripts/venice.py chat \"Summarize: https://example.com/article\" --web-scrape\n\nUncensored Mode\n# Use Venice's own uncensored model\npython3 {baseDir}/scripts/venice.py chat \"Your question\" --model venice-uncensored\n\n# Disable Venice system prompts for raw model output\npython3 {baseDir}/scripts/venice.py chat \"Your prompt\" --no-venice-system-prompt\n\nReasoning Models\n# Use a reasoning model with effort control\npython3 {baseDir}/scripts/venice.py chat \"Solve this math problem...\" --model kimi-k2-5 --reasoning-effort high\n\n# Strip thinking from output\npython3 {baseDir}/scripts/venice.py chat \"Debug this code\" --model qwen3-4b --strip-thinking\n\nAdvanced Options\n# Temperature and token control\npython3 {baseDir}/scripts/venice.py chat \"Be creative\" --temperature 1.2 --max-tokens 4000\n\n# JSON output mode\npython3 {baseDir}/scripts/venice.py chat \"List 5 colors as JSON\" --json\n\n# Prompt caching (for repeated context)\npython3 {baseDir}/scripts/venice.py chat \"Question\" --cache-key my-session-123\n\n# Show usage stats\npython3 {baseDir}/scripts/venice.py chat \"Hello\" --show-usage\n\nEmbeddings\n\nGenerate vector embeddings for semantic search, RAG, and recommendations:\n\n# Single text\npython3 {baseDir}/scripts/venice.py embed \"Venice is a private AI platform\"\n\n# Multiple texts (batch)\npython3 {baseDir}/scripts/venice.py embed \"first text\" \"second text\" \"third text\"\n\n# From file (one text per line)\npython3 {baseDir}/scripts/venice.py embed --file texts.txt\n\n# Output as JSON\npython3 {baseDir}/scripts/venice.py embed \"some text\" --output json\n\n\nModel: text-embedding-bge-m3 (private, $0.15/M tokens)\n\nText-to-Speech (TTS)\n\nConvert text to speech with 60+ multilingual voices:\n\n# Default voice\npython3 {baseDir}/scripts/venice.py tts \"Hello, welcome to Venice AI\"\n\n# Choose a voice\npython3 {baseDir}/scripts/venice.py tts \"Exciting news!\" --voice af_nova\n\n# List available voices\npython3 {baseDir}/scripts/venice.py tts --list-voices\n\n# Custom output path\npython3 {baseDir}/scripts/venice.py tts \"Some text\" --output /tmp/speech.mp3\n\n# Adjust speed\npython3 {baseDir}/scripts/venice.py tts \"Speaking slowly\" --speed 0.8\n\n\nPopular voices: af_sky, af_nova, am_liam, bf_emma, zf_xiaobei (Chinese), jm_kumo (Japanese)\n\nModel: tts-kokoro (private, $3.50/M characters)\n\nSpeech-to-Text (Transcription)\n\nTranscribe audio files to text:\n\n# Transcribe a file\npython3 {baseDir}/scripts/venice.py transcribe audio.wav\n\n# With timestamps\npython3 {baseDir}/scripts/venice.py transcribe recording.mp3 --timestamps\n\n# From URL\npython3 {baseDir}/scripts/venice.py transcribe --url https://example.com/audio.wav\n\n\nSupported formats: WAV, FLAC, MP3, M4A, AAC, MP4\n\nModel: nvidia/parakeet-tdt-0.6b-v3 (private, $0.0001/audio second)\n\nCheck Balance\npython3 {baseDir}/scripts/venice.py balance\n\nPart 2: Images & Video\nPricing Overview\nFeature\tCost\nImage generation\t~$0.01-0.03 per image\nImage upscale\t~$0.02-0.04\nImage edit\t$0.04\nVideo (WAN)\t~$0.10-0.50\nVideo (Sora)\t~$0.50-2.00\nVideo (Runway)\t~$0.20-1.00\n\nUse --quote with video commands to check pricing before generation.\n\nImage Generation\n# Basic generation\npython3 {baseDir}/scripts/venice-image.py --prompt \"a serene canal in Venice at sunset\"\n\n# Multiple images\npython3 {baseDir}/scripts/venice-image.py --prompt \"cyberpunk city\" --count 4\n\n# Custom dimensions\npython3 {baseDir}/scripts/venice-image.py --prompt \"portrait\" --width 768 --height 1024\n\n# List available models and styles\npython3 {baseDir}/scripts/venice-image.py --list-models\npython3 {baseDir}/scripts/venice-image.py --list-styles\n\n# Use specific model and style\npython3 {baseDir}/scripts/venice-image.py --prompt \"fantasy\" --model flux-2-pro --style-preset \"Cinematic\"\n\n# Reproducible results with seed\npython3 {baseDir}/scripts/venice-image.py --prompt \"abstract\" --seed 12345\n\n\nKey flags: --prompt, --model (default: flux-2-max), --count, --width, --height, --format (webp/png/jpeg), --resolution (1K/2K/4K), --aspect-ratio, --negative-prompt, --style-preset, --cfg-scale (0-20), --seed, --safe-mode, --hide-watermark, --embed-exif\n\nImage Upscale\n# 2x upscale\npython3 {baseDir}/scripts/venice-upscale.py photo.jpg --scale 2\n\n# 4x with AI enhancement\npython3 {baseDir}/scripts/venice-upscale.py photo.jpg --scale 4 --enhance\n\n# Enhanced with custom prompt\npython3 {baseDir}/scripts/venice-upscale.py photo.jpg --enhance --enhance-prompt \"sharpen details\"\n\n# From URL\npython3 {baseDir}/scripts/venice-upscale.py --url \"https://example.com/image.jpg\" --scale 2\n\n\nKey flags: --scale (1-4, default: 2), --enhance (AI enhancement), --enhance-prompt, --enhance-creativity (0.0-1.0), --url, --output\n\nImage Edit\n\nAI-powered image editing:\n\n# Add elements\npython3 {baseDir}/scripts/venice-edit.py photo.jpg --prompt \"add sunglasses\"\n\n# Modify scene\npython3 {baseDir}/scripts/venice-edit.py photo.jpg --prompt \"change the sky to sunset\"\n\n# Remove objects\npython3 {baseDir}/scripts/venice-edit.py photo.jpg --prompt \"remove the person in background\"\n\n# From URL\npython3 {baseDir}/scripts/venice-edit.py --url \"https://example.com/image.jpg\" --prompt \"colorize\"\n\n\nNote: The edit endpoint uses Qwen-Image which has some content restrictions.\n\nVideo Generation\n# Get price quote first\npython3 {baseDir}/scripts/venice-video.py --quote --model wan-2.6-image-to-video --duration 10s\n\n# Image-to-video (WAN - default)\npython3 {baseDir}/scripts/venice-video.py --image photo.jpg --prompt \"camera pans slowly\" --duration 10s\n\n# Image-to-video (Sora)\npython3 {baseDir}/scripts/venice-video.py --image photo.jpg --prompt \"cinematic\" \\\n  --model sora-2-image-to-video --duration 8s --aspect-ratio 16:9 --skip-audio-param\n\n# Video-to-video (Runway Gen4)\npython3 {baseDir}/scripts/venice-video.py --video input.mp4 --prompt \"anime style\" \\\n  --model runway-gen4-turbo-v2v\n\n# List models with available durations\npython3 {baseDir}/scripts/venice-video.py --list-models\n\n\nKey flags: --image or --video, --prompt, --model (default: wan-2.6-image-to-video), --duration, --resolution (480p/720p/1080p), --aspect-ratio, --audio/--no-audio, --quote, --timeout\n\nModels:\n\nWAN — Image-to-video, configurable audio, 5s-21s\nSora — Requires --aspect-ratio, use --skip-audio-param\nRunway — Video-to-video transformation\nTips & Ideas\n🔍 Web Search + LLM = Research Assistant\n\nUse --web-search on --web-citations to build a research workflow. Venice searches the web, synthesizes results, and cites sources — all in one API call.\n\n🔓 Uncensored Creative Content\n\nVenice's uncensored models work for both text AND images. No guardrails blocking legitimate creative use cases.\n\n🎯 Prompt Caching for Agents\n\nIf you're running an agent loop that sends the same system prompt repeatedly, use --cache-key to get up to 90% cost savings.\n\n🎤 Audio Pipeline\n\nCombine TTS and transcription: generate spoken content with tts, process audio with transcribe. Both are private inference.\n\n🎬 Video Workflow\nGenerate or find a base image\nUse --quote to estimate video cost\nGenerate with appropriate duration/model\nVideos take 1-5 minutes depending on settings\nTroubleshooting\nProblem\tSolution\nVENICE_API_KEY not set\tSet env var or configure in ~/.clawdbot/clawdbot.json\nInvalid API key\tVerify at venice.ai/settings/api\nModel not found\tRun --list-models to see available; use --no-validate for new models\nRate limited\tCheck --show-usage output\nVideo stuck\tVideos can take 1-5 min; use --timeout 600 for long ones\nResources\nAPI Docs: docs.venice.ai\nStatus: veniceai-status.com\nDiscord: discord.gg/askvenice"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/jonisjongithub/venice-ai",
    "publisherUrl": "https://clawhub.ai/jonisjongithub/venice-ai",
    "owner": "jonisjongithub",
    "version": "2.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/venice-ai",
    "downloadUrl": "https://openagent3.xyz/downloads/venice-ai",
    "agentUrl": "https://openagent3.xyz/skills/venice-ai/agent",
    "manifestUrl": "https://openagent3.xyz/skills/venice-ai/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/venice-ai/agent.md"
  }
}