Cumulus LabsBack to Leaderboard
Audio
F5-TTS
+6.2%~$F5TTS
Zero-shot voice cloning TTS model. Clone any voice from 10 seconds of reference audio. Fairytaler Finetuned Flow Matching architecture for natural prosody.
Deploy Now
#26 overall · 1 deploys
540ms
Cold Start
avg on Ion
650ms
Avg Inference
per request
1
Active Replicas
right now
1
Total Deployments
all time
7-Day Trend
+6.2% this weekCold Start vs Competitors
Lower is better●~$F5TTS540ms
~$ORPH820ms
~$DIA680ms
Cold start comparison vs similar models. Lower is better.
Cost Estimate
Cost per 1K Inferences
$0.75
Est. Daily (1K req/day)
$0.75
Est. Monthly (30K req)
$22.50
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
Quick Deploy
cumulus-sdkimport cumulus from "cumulus-sdk" // Deploy F5-TTS on Ion const client = await cumulus.deploy("f5-tts") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })