Genblaze

Pipeline SDK for AI-generated video, audio, and images with built-in provenance.

Genblaze is an AI pipeline SDK by Backblaze for building and orchestrating generative media workflows across video, image, and audio.

A unified Pipeline API spans providers like OpenAI, Google, Runway, Luma, ElevenLabs, and Stability Audio, plus models served through platforms such as GMI Cloud and NVIDIA NIM (build.nvidia.com) — so you swap providers without rewriting orchestration. Every run produces a canonical provenance manifest you can embed directly into media files (.mp4, .png, .mp3, …) and persist to Backblaze B2 or any S3-compatible store. Manifest.verify() checks the manifest hash and requires every output asset to declare a valid sha256; callers that fetch asset.url should re-hash those bytes separately, and the CLI's opt-in genblaze verify --fetch mode does exactly that.

Why Genblaze

Genblaze sits between "call a single video API" and "run a media pipeline in production." The differentiators:

• Provenance by default. Every run yields a canonical manifest — deterministic, embeddable into .mp4 / .png / .jpg / .webp / .mp3 / .wav, or persisted alongside the asset. Outputs become SHA-256-covered when providers return bytes or ObjectStorageSink transfers them into durable storage; URL-only outputs do not pass Manifest.verify(). Tamper-evident in trusted storage; pair with your own signer or C2PA when adversarial verification matters. See trust modes.
• One pipeline, many providers. Eleven adapters across video, image, audio, and chat behind a single Pipeline / Step API. Swap Sora → Runway → Veo by changing one line; chain text → image → video without re-plumbing.
• Storage is first-class. S3StorageBackend.for_backblaze("bucket") ships durable, credential-free asset URLs and content-addressable layouts. Designed for Backblaze B2; works against any S3-compatible store (AWS S3, Cloudflare R2, MinIO).
• Fallback chains and conformance. fallback_models=[...] retries on MODEL_ERROR; CI-grade probe_models and provider-contract tests catch upstream drift before users do.
• Replayable runs. Every manifest captures the full provenance — provider, model, prompt, params, timestamps — so a run can be reconstructed via genblaze replay manifest.json or by feeding the canonical params back into a Pipeline.

Reach for something else when:

• You only need an LLM chat loop → use the provider's SDK or LangChain.
• You're building a UI-driven generation app in JS/TS → use the Vercel AI SDK.
• You're not generating media or don't care about provenance → the provider's SDK directly is simpler.

Install

pip install genblaze                  # core + B2/S3 storage (the umbrella)
pip install "genblaze[gmicloud]"      # + GMICloud provider
pip install "genblaze[video]"         # + curated video bundle
pip install "genblaze[all]"           # + every provider

The umbrella pulls in genblaze-core (pipeline + models) and genblaze-s3 (Backblaze B2 / S3 storage) so you have a working provenance pipeline out of the box. Provider adapters are opt-in extras.

A GitHub Release tag (e.g. v0.7.0) is not a genblaze version — don't pin genblaze==. The tag names a CHANGELOG wave; every package in that wave versions independently, so wave tags and the umbrella's PyPI versions are separate sequences that happen to look alike (see RELEASING.md). A pin on a wave tag either:

• fails outright (no such version was published), or
• resolves silently to an unrelated umbrella build from a different wave — no error, just stale code (e.g. genblaze==0.4.0 on PyPI predates the v0.4.0 wave).

Pin the exact umbrella version instead (from that wave's "Released package versions" list in its release notes) — but note the umbrella pins ranges (e.g. genblaze-core>=0.3.8, even that isn't fully reproducible on its own. For a locked install, generate a lockfile (pip freeze, uv lock`, or a constraints file) once your stack works.

Install packages individually if you prefer:

pip install genblaze-core            # Pipeline, Step, Run, Manifest, sinks, tracers
pip install genblaze-s3              # S3-compatible storage (B2, AWS, R2, MinIO)
pip install genblaze-cli             # CLI: extract, verify, replay, index

# Provider adapters
pip install genblaze-openai          # OpenAI: Sora, DALL-E / gpt-image, TTS, chat
pip install genblaze-google          # Google: Veo, Imagen, Gemini-image, chat
pip install genblaze-nvidia          # NVIDIA NIM: Cosmos, SDXL/FLUX, Fugatto, Riva, chat
pip install genblaze-gmicloud        # GMICloud: video, image, audio, chat (request queue)
pip install genblaze-runway          # Runway Gen video
pip install genblaze-luma            # Luma Dream Machine video
pip install genblaze-decart          # Decart Lucy video / image
pip install genblaze-replicate       # Replicate (Flux, SDXL, etc.)
pip install genblaze-elevenlabs      # ElevenLabs TTS + sound effects
pip install genblaze-stability-audio # Stability AI Stable Audio (music)
pip install genblaze-lmnt            # LMNT fast TTS
pip install genblaze-hume            # Hume AI Octave TTS
pip install genblaze-assemblyai      # AssemblyAI speech-to-text / transcription

Install names use hyphens, Python imports use underscores: pip install genblaze- → import genblaze_.

TypeScript types for the manifest schema are published on npm:

npm install @genblaze/spec

Quickstart

End-to-end: generate a video, persist it and its provenance manifest to Backblaze B2, verify the hash.

pip install genblaze-core genblaze-gmicloud genblaze-s3

export GMI_API_KEY="gmi-..."
export B2_KEY_ID="..."
export B2_APP_KEY="..."

from genblaze_core import Modality, ObjectStorageSink, KeyStrategy, Pipeline
from genblaze_gmicloud import GMICloudVideoProvider
from genblaze_s3 import S3StorageBackend

storage = ObjectStorageSink(
    S3StorageBackend.for_backblaze("my-bucket"),
    key_strategy=KeyStrategy.HIERARCHICAL,
)

result = (
    Pipeline("my-first-pipeline")
    .step(
        GMICloudVideoProvider(),
        model="seedance-2-0-260128",
        prompt="A drone shot soaring over a coastal city at golden hour",
        modality=Modality.VIDEO,
        duration=10,
        aspect_ratio="16:9",
    )
    .run(sink=storage, timeout=600)
)

print(f"Asset URL: {result.run.steps[0].assets[0].url}")    # B2 durable URL
print(f"SHA-256:   {result.run.steps[0].assets[0].sha256}")
print(f"Manifest:  {result.manifest.manifest_uri}")         # Provenance JSON in B2
print(f"Hash:      {result.manifest.canonical_hash}")
print(f"Verified:  {result.manifest.verify()}")

The manifest captures the full provenance chain — provider, model, prompt, parameters, timestamps, and a canonical hash for integrity verification — and is uploaded alongside the asset. The asset URL is durable (credential-free, never expires), safe to store anywhere.

Runnable copy: examples/quickstart.py. No API key? Try examples/quickstart_local.py — builds and verifies a manifest with zero external calls.

Concepts