Text to image in about two seconds with eight-step distilled model
AI audio and video transcription platform with 2-pass multimodal accuracy
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
FR
Pricing model
Freemium
Freemium
Pricing
Free credits available; paid annual plans with 50% launch discount: Basic $9.9/month (800 credits/month, 9600 credits/year), Professional $19.9/month (2000 credits/month, 24000 credits/year), Enterprise $44.9/month (6000 credits/month, 72000 credits/year). Monthly plans also available. Per-render co
60 minutes free trial with no credit card required. Pro & Team Plan: €30 excluding VAT per month for 20 hours (€1.50/hour, 5 seats, unused hours roll over). Lifetime Credit Packs: €2.50 to €3.75 excluding VAT per hour (2h Discovery pack at €7.50, 5h, 10h, or 50h packs that never expire). Certified H
Key features
Eight-step sampling produces 1024px drafts in roughly two seconds
Text to image and image to image workflows in one workspace
Support for LoRA attachments with no extra render cost
Resolution from small exploratory sizes up to 2K
Open weights published under custom licence permitting commercial use
Photographic base behaviour from 12B model trained from scratch
LoRAs behave as bipolar sliders for intensity control mid-series
Browser-based workspace with no GPU or local install required
Same 12B backbone as standard Krea 2 via trajectory distillation
Unlimited exports in PNG, JPG and WebP formats
2-pass multimodal audio and video transcription via Google Cloud Vertex AI
Support for 100+ languages and bilingual code-switching
Automatic speaker identification and diarization with 1-click renaming
Synchronized interactive playback player
Export to Word (.docx), PDF, and Subtitles (.srt, .vtt)
AES-256 encrypted storage in France on OVHcloud
Zero Data Retention with Google Cloud Vertex AI inference
Process recordings up to 10 continuous hours without cutoffs
Support for Olympus and Philips dictaphone formats (.ds2, .dss)
Certified human proofreading with dual-transcriber cross-check
What makes it different
Two-second generation speed enables iteration-heavy workflows instead of single-frame rendering
Open weights allow running the same model locally without vendor lock-in
Trajectory distillation preserves detail of full 12B model at eight-step speed
2.5x fewer manual corrections required than market average
Direct multimodal acoustic processing avoids hallucinated loops of traditional pipelines
Seamless bilingual code-switching without manual configuration
GDPR compliant with strict Zero Data Retention and 1-click file deletion
Invisible audio stitching technology handles long recordings from 10 seconds to 10 hours
Krea 2 Turbo
Le Scribe Audio