genblaze-lmnt 0.3.0

LMNT text-to-speech provider adapter for genblaze

genblaze-lmnt

LMNT ultra-low-latency text-to-speech provider adapter for genblaze — real-time AI voice pipelines with SHA-256 provenance manifests on every clip.

genblaze-lmnt wraps LMNT's sub-second TTS API as a genblaze provider — ideal for real-time agent voices, live narration, and interactive media where latency matters. Compose into multi-step AI pipelines, persist outputs to Backblaze B2 or any S3-compatible store, and emit a tamper-evident provenance manifest for every run.

Why genblaze-lmnt

• Ultra-low latency — LMNT is optimized for real-time voice; pairs well with genblaze AgentLoop.
• Provenance by default — SHA-256-verified manifest on every clip; embed manifest directly into MP3.
• Production-ready — retries, timeouts, step caching, moderation hooks.
• Composable — chain LMNT narration with music (Stable Audio) + FFmpeg AV compositing.
• Durable storage — plug genblaze-s3 in for Backblaze B2 / AWS S3 / R2 / MinIO persistence.

Models

Model	Notes
lmnt-1	LMNT's fast TTS model

Install

pip install genblaze-lmnt

Registers the lmnt provider via entry points; genblaze-core discovers it automatically.

Quickstart — LMNT TTS

pip install genblaze-core genblaze-lmnt
export LMNT_API_KEY="..."

from genblaze_core import Modality, Pipeline
from genblaze_lmnt import LMNTProvider

run, manifest = (
    Pipeline("lmnt-tts-demo")
    .step(LMNTProvider(output_dir="output/audio"),
          model="lmnt-1",
          prompt="The quick brown fox jumps over the lazy dog.",
          modality=Modality.AUDIO, voice="lily")
    .run(timeout=30)
)
print(run.steps[0].assets[0].url, manifest.canonical_hash)

Persist to Backblaze B2

from genblaze_core import KeyStrategy, ObjectStorageSink
from genblaze_s3 import S3StorageBackend

storage = ObjectStorageSink(
    S3StorageBackend.for_backblaze("my-bucket"),
    key_strategy=KeyStrategy.HIERARCHICAL,
)
# pass sink=storage to .run(…)

Backblaze B2 is the recommended default sink for AI-generated audio.

Credentials

Env var	Where to get it
LMNT_API_KEY	https://app.lmnt.com/account

Documentation

• Main repo: https://github.com/backblaze-labs/genblaze
• Example: lmnt_tts_pipeline.py

Related packages

• genblaze-core — the pipeline SDK
• genblaze-s3 — durable storage on Backblaze B2 and other S3-compatible backends
• Other audio providers: genblaze-elevenlabs (TTS + SFX) · genblaze-openai (TTS) · genblaze-stability-audio (music) · genblaze-gmicloud

License

MIT