Creative agency / product studioGirard Media

How Girard Media ships talk-to-timeline cuts on its own fleet

Girard Media runs CoreReflex as the production layer for speech-native video — self-hosted transcription, deterministic cut, editable .cr, and karaoke-captioned MP4 with zero premium API spend on the path.

Self-hosted Whisper STT
Zero vendor cents on the Cut path
Public gallery films live on corereflex.com
Remotion render queue draining on own fleet

The speech-native path is the wedge — raw take in, editable cut out, on our fleet.

Steve Girard, Founder

Challenge

Agency production still pays twice: once for people who can cut, and again for cloud APIs that meter every second of speech and generation. Girard Media needed a path that stays honest (no fake stems, no silent vendor hop) and stays on owned infrastructure.

Workflow

  1. Ingest a talking-head take into Files (workspace assets).
  2. Talk to timeline — the starter pipeline: own Whisper → deterministic cut → karaoke caption burn → fleet render.
  3. Open the editable project (.cr) in the studio; refine with natural-language edits when needed.
  4. Publish proof — finished films can land in the public gallery when marked public.

Result

Evidence

Operator-owned product and production stack. Metrics above are from production health and the Native Wow through-path, not a paid-customer pilot. Customer case studies will land here as they are approved.

Live deliverable (2026-07-30 fleet smoke)

Want a production system with this much traceability?

Start free

← All case studies