{"id":"realtime-tts","slug":"realtime-tts","name":"Ultra-low-latency text-to-speech","shortName":"Ultra-low-latency text-to-speech","problemStatement":"Voice agents need streaming TTS with minimal time-to-first-audio.","whenNotTopPick":"Need largest voice library — ElevenLabs; already standardized on Deepgram Voice Agent; need expressive/empathic TTS — Hume. PlayHT/PlayAI is sunset (Meta) — do not pick.","categoryIds":["cat-media-gen"],"depotPickProviderId":"cartesia","depotPickRationale":"Latency capability + pricePerf.","runnersUpIds":["elevenlabs","deepgram","hume","rime"],"weights":{"capabilityFit":0.2,"pricePerformance":0.15,"latencyReliability":0.3,"developerDx":0.15,"privacyPosture":0.08,"lockInRisk":0.05,"maturity":0.07},"methodologyNotes":"Latency capability + pricePerf.","tags":["realtime"],"depth":{"whenNotToUse":{"text":"Need largest voice library — ElevenLabs; already standardized on Deepgram Voice Agent; need expressive/empathic TTS — Hume. PlayHT/PlayAI is sunset (Meta) — do not pick.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"elevenlabs","name":"ElevenLabs","overallForJob":8.4,"pickOverallForJob":7.85,"beatsPickOn":["capabilityFit","latencyReliability","developerDx","maturity"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":4.5,"runnerUpLockInRisk":5.5,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":[],"runnerUpExitSignals":[],"pickNotes":[],"selfHostFallback":[{"id":"kokoro-82m","name":"Kokoro-82M","license":"Apache-2.0","sourceUrl":"https://huggingface.co/hexgrad/Kokoro-82M/raw/main/README.md"},{"id":"piper","name":"Piper","license":"MIT","sourceUrl":"https://raw.githubusercontent.com/rhasspy/piper/master/LICENSE.md"}],"migration":"The pick has lower stored lock-in risk than runner-up ElevenLabs (4.5 vs 5.5). Self-host fallback listed for this job: Kokoro-82M, Piper.","migrationReason":null,"derivedFrom":"stored lockInRisk scores, provider tags (oss, self-host, openai-compat, open-models), free rows that list this job, and verbatim provider notes. No migration guide was invented."}},"freshness":{"pick":{"score":{"asOf":"2026-09-14","ageDays":43,"stale":true,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-09-14","ageDays":43,"stale":true,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-27","sourceUrls":3,"sourcesReachable":3,"pricingRows":0,"pricingRowsReconfirmed":0,"note":"A source re-check confirms the page is reachable and, for pricing rows, that the stored amount and SKU name appear on it. It does not re-derive or change the score.","reason":null}}},"depotPick":{"id":"cartesia","slug":"cartesia","name":"Cartesia","tagline":"Top pick for realtime low-latency voice agents. ElevenLabs for voice library breadth.","overall":7.85},"runnersUp":[{"id":"elevenlabs","slug":"elevenlabs","name":"ElevenLabs","tagline":"Default voice layer for talking agents. Combine with Twilio for phone; watch cloning policy.","overall":8.4},{"id":"deepgram","slug":"deepgram","name":"Deepgram","tagline":"Default STT and strong voice-agent platform. Standard Flux TTS / Voice Agent rates live since 2026-09-15…","overall":8.54},{"id":"hume","slug":"hume","name":"Hume AI","tagline":"A/B vs Cartesia when emotional prosody is the product. Cartesia remains the low-latency default; ElevenLabs…","overall":7.69},{"id":"rime","slug":"rime","name":"Rime","tagline":"Realtime TTS latency peer. Depot pick stays Cartesia; ElevenLabs for library; Hume expressive; Rime when Mist…","overall":8.33}]}