Cumulus LabsBack to Leaderboard
Audio
Dia 1.6B
+8.4%~$DIA
Dialogue-focused TTS model at 1.6B scale. Generates natural multi-speaker conversations including laughter, sighs, and nonverbal sounds. Built for voice agents.
Deploy Now
#25 overall · 1 deploys
680ms
Cold Start
avg on Ion
890ms
Avg Inference
per request
1
Active Replicas
right now
1
Total Deployments
all time
7-Day Trend
+8.4% this weekCold Start vs Competitors
Lower is better●~$DIA680ms
~$ORPH820ms
~$F5TTS540ms
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$1.00
Est. Daily (1K req/day)
$1.00
Est. Monthly (30K req)
$30.00
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy Dia 1.6B on Ion const client = await cumulus.deploy("dia-1-6b") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })