Skip to main content
fluffbuzz infer is the canonical headless surface for provider-backed inference workflows. It intentionally exposes capability families, not raw gateway RPC names and not raw agent tool ids.

​
Turn infer into a skill

Copy and paste this to an agent: 
Read https://docs.fluffbuzz.com/cli/infer, then create a skill that routes my common workflows to `fluffbuzz infer`.
Focus on model runs, image generation, video generation, audio transcription, TTS, web search, and embeddings.
A good infer-based skill should:
  • map common user intents to the correct infer subcommand
  • include a few canonical infer examples for the workflows it covers
  • prefer fluffbuzz infer ... in examples and suggestions
  • avoid re-documenting the entire infer surface inside the skill body
Typical infer-focused skill coverage:
  • fluffbuzz infer model run
  • fluffbuzz infer image generate
  • fluffbuzz infer audio transcribe
  • fluffbuzz infer tts convert
  • fluffbuzz infer web search
  • fluffbuzz infer embedding create

​
Why use infer

fluffbuzz infer provides one consistent CLI for provider-backed inference tasks inside FluffBuzz. Benefits:
  • Use the providers and models already configured in FluffBuzz instead of wiring up one-off wrappers for each backend.
  • Keep model, image, audio transcription, TTS, video, web, and embedding workflows under one command tree.
  • Use a stable --json output shape for scripts, automation, and agent-driven workflows.
  • Prefer a first-party FluffBuzz surface when the task is fundamentally “run inference.”
  • Use the normal local path without requiring the gateway for most infer commands.

​
Command tree

 fluffbuzz infer
  list
  inspect

  model
    run
    list
    inspect
    providers
    auth login
    auth logout
    auth status

  image
    generate
    edit
    describe
    describe-many
    providers

  audio
    transcribe
    providers

  tts
    convert
    voices
    providers
    status
    enable
    disable
    set-provider

  video
    generate
    describe
    providers

  web
    search
    fetch
    providers

  embedding
    create
    providers

​
Common tasks

This table maps common inference tasks to the corresponding infer command.
TaskCommandNotes
Run a text/model promptfluffbuzz infer model run --prompt "..." --jsonUses the normal local path by default
Generate an imagefluffbuzz infer image generate --prompt "..." --jsonUse image edit when starting from an existing file
Describe an image filefluffbuzz infer image describe --file ./image.png --json--model must be an image-capable <provider/model>
Transcribe audiofluffbuzz infer audio transcribe --file ./memo.m4a --json--model must be <provider/model>
Synthesize speechfluffbuzz infer tts convert --text "..." --output ./speech.mp3 --jsontts status is gateway-oriented
Generate a videofluffbuzz infer video generate --prompt "..." --json
Describe a video filefluffbuzz infer video describe --file ./clip.mp4 --json--model must be <provider/model>
Search the webfluffbuzz infer web search --query "..." --json
Fetch a web pagefluffbuzz infer web fetch --url https://example.com --json
Create embeddingsfluffbuzz infer embedding create --text "..." --json

​
Behavior

  • fluffbuzz infer ... is the primary CLI surface for these workflows.
  • Use --json when the output will be consumed by another command or script.
  • Use --provider or --model provider/model when a specific backend is required.
  • For image describe, audio transcribe, and video describe, --model must use the form <provider/model>.
  • For image describe, an explicit --model runs that provider/model directly. The model must be image-capable in the model catalog or provider config. codex/<model> runs a bounded Codex app-server image-understanding turn; openai-codex/<model> uses the OpenAI Codex OAuth provider path.
  • Stateless execution commands default to local.
  • Gateway-managed state commands default to gateway.
  • The normal local path does not require the gateway to be running.

​
Model

Use model for provider-backed text inference and model/provider inspection. 
fluffbuzz infer model run --prompt "Reply with exactly: smoke-ok" --json
fluffbuzz infer model run --prompt "Summarize this changelog entry" --provider openai --json
fluffbuzz infer model providers --json
fluffbuzz infer model inspect --name gpt-5.5 --json
Notes:
  • model run reuses the agent runtime so provider/model overrides behave like normal agent execution.
  • model auth login, model auth logout, and model auth status manage saved provider auth state.

​
Image

Use image for generation, edit, and description. 
fluffbuzz infer image generate --prompt "friendly puppy illustration" --json
fluffbuzz infer image generate --prompt "cinematic product photo of headphones" --json
fluffbuzz infer image describe --file ./photo.jpg --json
fluffbuzz infer image describe --file ./ui-screenshot.png --model openai/gpt-4.1-mini --json
fluffbuzz infer image describe --file ./photo.jpg --model ollama/qwen2.5vl:7b --json
Notes:
  • Use image edit when starting from existing input files.
  • For image describe, --model must be an image-capable <provider/model>.
  • For local Ollama vision models, pull the model first and set OLLAMA_API_KEY to any placeholder value, for example ollama-local. See Ollama.

​
Audio

Use audio for file transcription. 
fluffbuzz infer audio transcribe --file ./memo.m4a --json
fluffbuzz infer audio transcribe --file ./team-sync.m4a --language en --prompt "Focus on names and action items" --json
fluffbuzz infer audio transcribe --file ./memo.m4a --model openai/whisper-1 --json
Notes:
  • audio transcribe is for file transcription, not realtime session management.
  • --model must be <provider/model>.

​
TTS

Use tts for speech synthesis and TTS provider state. 
fluffbuzz infer tts convert --text "hello from fluffbuzz" --output ./hello.mp3 --json
fluffbuzz infer tts convert --text "Your build is complete" --output ./build-complete.mp3 --json
fluffbuzz infer tts providers --json
fluffbuzz infer tts status --json
Notes:
  • tts status defaults to gateway because it reflects gateway-managed TTS state.
  • Use tts providers, tts voices, and tts set-provider to inspect and configure TTS behavior.

​
Video

Use video for generation and description. 
fluffbuzz infer video generate --prompt "cinematic sunset over the ocean" --json
fluffbuzz infer video generate --prompt "slow drone shot over a forest lake" --json
fluffbuzz infer video describe --file ./clip.mp4 --json
fluffbuzz infer video describe --file ./clip.mp4 --model openai/gpt-4.1-mini --json
Notes:
  • --model must be <provider/model> for video describe.

​
Web

Use web for search and fetch workflows. 
fluffbuzz infer web search --query "FluffBuzz docs" --json
fluffbuzz infer web search --query "FluffBuzz infer web providers" --json
fluffbuzz infer web fetch --url https://docs.fluffbuzz.com/cli/infer --json
fluffbuzz infer web providers --json
Notes:
  • Use web providers to inspect available, configured, and selected providers.

​
Embedding

Use embedding for vector creation and embedding provider inspection. 
fluffbuzz infer embedding create --text "friendly puppy" --json
fluffbuzz infer embedding create --text "customer support ticket: delayed shipment" --model openai/text-embedding-3-large --json
fluffbuzz infer embedding providers --json

​
JSON output

Infer commands normalize JSON output under a shared envelope: 
{
  "ok": true,
  "capability": "image.generate",
  "transport": "local",
  "provider": "openai",
  "model": "gpt-image-2",
  "attempts": [],
  "outputs": []
}
Top-level fields are stable:
  • ok
  • capability
  • transport
  • provider
  • model
  • attempts
  • outputs
  • error

​
Common pitfalls

# Bad
fluffbuzz infer media image generate --prompt "friendly puppy"

# Good
fluffbuzz infer image generate --prompt "friendly puppy"

# Bad
fluffbuzz infer audio transcribe --file ./memo.m4a --model whisper-1 --json

# Good
fluffbuzz infer audio transcribe --file ./memo.m4a --model openai/whisper-1 --json

​
Notes

  • fluffbuzz capability ... is an alias for fluffbuzz infer ....