One key. Every modality.
Router9 Tools give your agents and coding CLIs eyes, ears, and a voice. Generate images, synthesize speech, and read or transcribe any media — each powered by your choice of frontier models, all on one flat monthly plan.
Install in one line
Add Router9 Tools to your harness with OpenClaw, or wire them up via MCP for Claude Code, OpenCode, and other MCP clients.
openclaw skills install router9 --set ROUTER9_API_KEY=sk-r9k-...sk-r9k-... with your key. Sign up to get oneGenerate media
Multimedia output from a simple prompt — pictures, speech, and soon, video. Pick the model that fits your style and budget.
Image generation
Turn prompts into pictures
Render artwork, product shots, diagrams, and icons straight from a text prompt. Switch between models to trade off style, speed, and cost — no extra account or key required.
1 model available
google/gemini-3.1-flash-image-previewdefaultText to speech
Give your agent a voice
Convert any text into natural spoken audio with selectable voices. Perfect for voice agents, narration, accessibility, and notifications. Streams back ready-to-play audio.
1 model available
openai/gpt-4o-audio-previewdefaultVideo generation
SoonPrompts in, motion out
Generate short clips from a text prompt — the same flat-rate key, a new output modality. We're wiring up the best video models now; tell us what you'd build with it.
Understand media
Turn images and audio into text your agent can reason over — describe, read, and transcribe.
Image description
Eyes for your agent
Get rich, detailed descriptions of any image — scenes, objects, charts, UI screenshots. Pass your own prompt to steer what the model focuses on.
1 model available
google/gemini-2.0-flash-001defaultOCR — text from images
Read anything
Pull printed and handwritten text out of photos, scans, receipts, signs, and labels. Returns structured blocks with confidence scores plus the full text.
1 model available
google/gemini-2.0-flash-001defaultSpeech to text
Ears for your agent
Transcribe meetings, voice notes, and calls into clean text. Upload a file directly or point at a URL, and optionally hint the spoken language.
1 model available
openai/gpt-4o-audio-previewdefaultGuides & reference
Everything you need to ship — per-tool guides, usage quotas, and integration walkthroughs.