Cumulus LabsBack to Leaderboard
Audio
Orpheus 3B
+11.8%~$ORPH
3B text-to-speech model with natural prosody and emotional expressiveness. Low latency TTS for voice applications. Supports custom voice profiles and style control.
Deploy Now
#24 overall · 1 deploys
820ms
Cold Start
avg on Ion
1.2s
Avg Inference
per request
1
Active Replicas
right now
1
Total Deployments
all time
7-Day Trend
+11.8% this weekCold Start vs Competitors
Lower is better●~$ORPH820ms
~$DIA680ms
~$F5TTS540ms
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$1.50
Est. Daily (1K req/day)
$1.50
Est. Monthly (30K req)
$45.00
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy Orpheus 3B on Ion const client = await cumulus.deploy("orpheus-3b") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })