{"jtbd":{"id":"speech-synthesis","slug":"speech-synthesis","name":"Text-to-speech","shortName":"Text-to-speech","problemStatement":"Natural TTS for agents and products."},"pick":{"id":"elevenlabs","slug":"elevenlabs","name":"ElevenLabs","tagline":"Default voice layer for talking agents. Combine with Twilio for phone; watch cloning policy.","website":"https://elevenlabs.io","overall":8.27,"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.27,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"TTS/STS/voice agents; character/credit plans; telephony integrations (e.g. Twilio).","scores":{"capabilityFit":9.4,"pricePerformance":7.5,"latencyReliability":8.8,"developerDx":9,"privacyPosture":7,"lockInRisk":5.5,"maturity":8.8,"overall":8.27,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},"runnersUp":[{"id":"cartesia","slug":"cartesia","name":"Cartesia","tagline":"Top pick for realtime low-latency voice agents. ElevenLabs for voice library breadth.","website":"https://cartesia.ai","overall":7.81,"scoreBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"scoreLayers":{"editorialPrior":7.81,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14: Credit plans — Free $0 (20k credits), Pro $5 (100k), Startup $49 (1.25M), Scale $299 (8M) + prepaid agent minutes. Sonic TTS + Ink STT + voice agents. Cartesia phone numbers ~$0.014/min. Ultra-low-latency voice narrative.","scores":{"capabilityFit":8.4,"pricePerformance":8,"latencyReliability":7.8,"developerDx":8.4,"privacyPosture":7.5,"lockInRisk":4.5,"maturity":7,"overall":7.81,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"openai-media","slug":"openai-media","name":"OpenAI Media (Images/Audio)","tagline":"Convenient if you're already on OpenAI. For best image variety/cost, keep Fal in the toolkit.","website":"https://platform.openai.com/docs/guides/images","overall":8.15,"scoreBand":{"low":7.6,"mid":8.2,"high":8.8,"halfWidth":0.6,"basis":"editorial_prior","display":"7.6–8.8 (editorial prior)"},"scoreLayers":{"editorialPrior":8.15,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Image generation, TTS, Whisper/transcription via OpenAI API; billed per image/minute/token as applicable.","scores":{"capabilityFit":8.8,"pricePerformance":7.2,"latencyReliability":8.8,"developerDx":9.2,"privacyPosture":7.8,"lockInRisk":7,"maturity":9.6,"overall":8.15,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"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…","website":"https://www.hume.ai","overall":7.63,"scoreBand":{"low":7,"mid":7.6,"high":8.2,"halfWidth":0.6,"basis":"editorial_prior","display":"7.0–8.2 (editorial prior)"},"scoreLayers":{"editorialPrior":7.63,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14 (hume.ai/pricing): Tiered Free → Creator → Team → Enterprise. EVI 3 additional usage $0.04/min (pinned). Team: 5 seats, 30 concurrent connections, unlimited voice create/use. Enterprise: custom characters/EVI, unlimited seats/concurrency, SOC2/GDPR/HIPAA. Included character bundles and Creator list $ are JS-rendered — verify in console; EVI unit price is solid.","scores":{"capabilityFit":8.6,"pricePerformance":7,"latencyReliability":7.8,"developerDx":8,"privacyPosture":7.8,"lockInRisk":5,"maturity":7.2,"overall":7.63,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"minimax","slug":"minimax","name":"MiniMax","tagline":"Primary indie-usable Chinese multimodal API alongside Moonshot. Prefer Anthropic/OpenAI for coding agents…","website":"https://www.minimax.io","overall":7.83,"scoreBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"scoreLayers":{"editorialPrior":7.83,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14 (platform.minimax.io/docs/guides/pricing-paygo): International api.minimax.io (OpenAI + Anthropic-compat). MiniMax-M3 ≤512k: list $0.60/$2.40 → permanent 50% off $0.30/$1.20 per 1M (cache read $0.06); >512k $0.60/$2.40 after promo. Priority tier 1.5×. M2.7 $0.30/$1.20 (highspeed $0.60/$2.40). TTS speech-2.8-turbo $60/M chars, hd $100/M. ASR $0.38/hr. Video H3 768P $0.08/s / 2K $0.13/s. image-01 $0.0035. Token Plan (Plus/Max/Ultra) is closed to new purchases; its figure was removed. It is replaced by M Plan, listed at platform.minimax.io/docs/m-plan/monthly-offer as of 2026-10-21 at regular prices of Go $22/month, Explore $55/month and Build $132/month (first month 50% off; not stored as rows). Mainland keys use api.minimaxi.com — not interchangeable.","scores":{"capabilityFit":8.4,"pricePerformance":8.8,"latencyReliability":7.8,"developerDx":8.2,"privacyPosture":6.2,"lockInRisk":4.8,"maturity":7.6,"overall":7.83,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"rime","slug":"rime","name":"Rime","tagline":"Realtime TTS latency peer. Depot pick stays Cartesia; ElevenLabs for library; Hume expressive; Rime when Mist…","website":"https://www.rime.ai","overall":8.27,"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.27,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14 (rime.ai/pricing): Mist v3 **$0.03/1k chars** (~$0.03/min); Coda **$0.05/1k chars**. Starter includes ~800 free minutes / ~3k free minutes on new accounts (marketing copy varies — confirm console). Enterprise volume + VPC/on-prem + BAA. Claimed Mist TTFA P50 ~37ms.","scores":{"capabilityFit":8.6,"pricePerformance":8.8,"latencyReliability":8.4,"developerDx":8.6,"privacyPosture":8.4,"lockInRisk":4.2,"maturity":7.4,"overall":8.27,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}}],"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.27,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"whyPickOverHigherScore":{"pickId":"elevenlabs","pickName":"ElevenLabs","pickScore":8.27,"highestScoredCandidateId":"elevenlabs","highestScoredCandidateName":"ElevenLabs","highestScore":8.27,"pickHasLowerCompositeScore":false,"delta":0,"pickLeadsOnDimensions":[],"explanation":"ElevenLabs (8.27) holds both the highest composite score among ranked candidates and the editorial pick for Text-to-speech: capability voice quality + dx."},"cheapest":{"providerId":"deepgram","providerName":"Deepgram","skuId":"deepgram-aura-2-payg","item":"Aura-2","plan":"Aura-2 — Pay As You Go","unit":"usd_per_1k_characters","amountUsd":0.03,"isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuCountInUnit":2,"isDepotPick":false,"sourceUrl":"https://deepgram.com/pricing","asOf":"2026-10-03","verifiedAsOf":"2026-10-27"},"recommendedWorkloadQuote":{"providerId":"elevenlabs","providerName":"ElevenLabs","skuId":"elevenlabs-tts-v4-turbo","item":"v4 Turbo Text to Speech","plan":"v4 Turbo Text to Speech — Price per 1K characters on the API card and every tier of the Text to Speech API table (rendered 2026-10-19)","unit":"usd_per_1k_characters","amountUsd":0.04,"outputSkuId":null,"outputItem":null,"outputAmountUsd":null,"outputUnit":null,"sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-19","pricingLastVerifiedAt":"2026-10-27","isFlagshipForJob":false,"differsFromFloorCheapest":false,"representativeQuote":{"skuId":"elevenlabs-tts-v4-turbo","item":"v4 Turbo Text to Speech","plan":"v4 Turbo Text to Speech — Price per 1K characters on the API card and every tier of the Text to Speech API table (rendered 2026-10-19)","amountUsd":0.04,"inputOrUnitUsd":0.04,"unit":"usd_per_1k_characters","outputUsd":null,"outputUnit":null,"sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-19"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"unitsPerTask":1,"baseCostPer1kTasksUsd":0.04,"totalUsd":0.046,"estimatedTotalUsd":0.046,"perTaskUsd":0.000046,"estimatedCostPerTaskUsd":0.000046,"formula":"(1,000 calls @ $0.04/1k_characters) * 1.15 overhead","assumptions":"1,000 tasks @ 1 request/task with 1.15x retry/tool-call overhead."}},"representativeQuote":{"skuId":"elevenlabs-tts-v4-turbo","item":"v4 Turbo Text to Speech","plan":"v4 Turbo Text to Speech — Price per 1K characters on the API card and every tier of the Text to Speech API table (rendered 2026-10-19)","amountUsd":0.04,"inputOrUnitUsd":0.04,"unit":"usd_per_1k_characters","outputUsd":null,"outputUnit":null,"sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-19"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"unitsPerTask":1,"baseCostPer1kTasksUsd":0.04,"totalUsd":0.046,"estimatedTotalUsd":0.046,"perTaskUsd":0.000046,"estimatedCostPerTaskUsd":0.000046,"formula":"(1,000 calls @ $0.04/1k_characters) * 1.15 overhead","assumptions":"1,000 tasks @ 1 request/task with 1.15x retry/tool-call overhead."},"freeAlternatives":[{"id":"cloudflare-workers-ai-tts","name":"Cloudflare Workers AI text-to-speech (MeloTTS, Aura-1)","kind":"free_speech","providerId":"cloudflare-workers-ai","jtbdIds":["speech-synthesis"],"whatYouGet":"@cf/myshell-ai/melotts and @cf/deepgram/aura-1 text-to-speech on the same shared 10,000 neurons/day free allocation as every Workers AI model. No separate free TTS cap is stated.","cost":"free","limits":{"sharedNeuronsPerDay":10000,"separateAudioCap":null},"sourceUrl":"https://developers.cloudflare.com/workers-ai/platform/pricing/","notes":"The audio pricing table (fetched 2026-10-19) lists @cf/myshell-ai/melotts at $0.0002 per audio minute and @cf/deepgram/aura-1 at $0.015 per 1k characters input, billed in neurons. Those are paid units, not free quotas; the free part is the shared daily neuron allocation.","license":null,"asOf":"2026-10-19","freeType":"free_speech","substitutable":true},{"id":"espeak-ng","name":"eSpeak NG","kind":"free_speech","jtbdIds":["speech-synthesis"],"whatYouGet":"Open-source local speech synthesizer.","cost":"oss","license":"GPL-3.0","sourceUrl":"https://raw.githubusercontent.com/espeak-ng/espeak-ng/master/COPYING","notes":"COPYING fetched 2026-10-03 is GNU GPL version 3. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): HTTP 200, no redirect, byte-identical: 'GNU GENERAL PUBLIC LICENSE Version 3, 29 June 2007'. License unchanged.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_speech","substitutable":true},{"id":"gemini-3.8-flash-tts-free-tier","name":"Gemini 3.8 Flash TTS free tier","kind":"free_speech","providerId":"google-ai","jtbdIds":["speech-synthesis","realtime-tts"],"whatYouGet":"gemini-3.8-flash-tts standard text input and audio output marked Free of charge. gemini-3.8-flash-lite-tts, gemini-3.1-flash-tts-preview and gemini-2.5-flash-preview-tts standard cells are also Free of charge.","cost":"free_tier_unspecified","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","notes":"Pricing page fetched twice 2026-10-26 (identical text; page footer 'Last updated 2026-10-26 UTC'): gemini-3.8-flash-tts is 'Our 3.8 Flash Text-to-Speech audio model engineered for studio-grade voice fidelity, expressive acting, and long-form stability.' Its Standard Free Tier input and output cells read 'Free of charge', as do those of gemini-3.8-flash-lite-tts, gemini-3.1-flash-tts-preview and gemini-2.5-flash-preview-tts ('Our 2.5 Flash text-to-speech audio model optimized for price-performant, low-latency, controllable speech generation.'). Batch TTS free tier is 'Not available' for 3.8 Flash TTS and 2.5 Flash Preview TTS. gemini-2.5-pro-preview-tts is not included: its Standard free-tier cells read 'Not available'. No numeric free audio cap. https://ai.google.dev/gemini-api/docs/rate-limits (fetched twice 2026-10-26, identical text, 'Last updated 2026-10-26 UTC') publishes no free-tier RPM, TPM or RPD and says 'View your active rate limits in AI Studio', so limits stay null. Re-quoted in v0.12.130 (previously fetched twice 2026-10-24, page footer 'Last updated 2026-10-22 UTC'); gemini-2.5-flash-preview-tts added to this row in v0.12.130 as a Depot data decision (approvalRef 'Ethan delegation 2026-10-21 19:41 ET t55u', decidedBy Agent Depo); no price stored, not a $0 price-sort row.","limits":null,"license":null,"asOf":"2026-10-26","freeType":"free_speech","substitutable":true},{"id":"groq-free-plan-orpheus","name":"Groq Free Plan Orpheus TTS","kind":"free_speech","providerId":"groq","jtbdIds":["speech-synthesis","realtime-tts"],"whatYouGet":"Free Plan text-to-speech limits for two Orpheus voices.","cost":"free","limits":{"scope":"organization","models":{"canopylabs/orpheus-arabic-saudi":{"rpm":10,"rpd":100,"tpm":1200,"tpd":3600},"canopylabs/orpheus-v1-english":{"rpm":10,"rpd":100,"tpm":1200,"tpd":3600}}},"sourceUrl":"https://console.groq.com/docs/rate-limits","notes":"Rate-limits page fetched twice 2026-10-24 about 10 s apart (identical HTML; the page shows no last-updated date). Same freeRows payload: canopylabs/orpheus-arabic-saudi and canopylabs/orpheus-v1-english both read RPM 10, RPD 100, TPM 1.2K, TPD 3.6K (unchanged). Same exception and account-page caveat as the chat row. Developer-plan numbers were not copied.","license":null,"asOf":"2026-10-24","freeType":"free_speech","substitutable":true},{"id":"kokoro-82m","name":"Kokoro-82M","kind":"open_weights","jtbdIds":["speech-synthesis","realtime-tts"],"whatYouGet":"Downloadable Kokoro 82M text-to-speech weights.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/hexgrad/Kokoro-82M/raw/main/README.md","notes":"Model card fetched 2026-10-03 says license: apache-2.0 and Apache-licensed weights. The repo LICENSE file path returned 404; the kokoro code LICENSE on GitHub was also fetched and is Apache-2.0. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0'; raw/main/LICENSE still 404 (twice); https://raw.githubusercontent.com/hexgrad/kokoro/main/LICENSE (HTTP 200) is 'Apache License Version 2.0, January 2004'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"piper","name":"Piper","kind":"free_speech","jtbdIds":["speech-synthesis","realtime-tts"],"whatYouGet":"Open-source local text-to-speech engine.","cost":"oss","license":"MIT","sourceUrl":"https://raw.githubusercontent.com/rhasspy/piper/master/LICENSE.md","notes":"LICENSE.md fetched 2026-10-03 is MIT, copyright 2022 Michael Hansen. Voice packs are a separate download; rhasspy/piper-voices card says license mit. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): HTTP 200, no redirect, byte-identical: 'MIT License' / 'Copyright (c) 2022 Michael Hansen'. License unchanged.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_speech","substitutable":true}],"referenceDocs":[],"falsification":{"jtbdId":"speech-synthesis","jtbdName":"Text-to-speech","currentPickId":"elevenlabs","currentPickScore":8.27,"challengerId":"cartesia","challengerScore":7.81,"currentScoreGap":0.46,"minVerifiedOutcomes":10,"requiredOutcomeMargin":0.61,"requiredSuccessRateDelta":0.15,"maxPickPriceIncreasePct":25,"whatWouldChangePick":["Cartesia (cartesia) outperforms ElevenLabs (elevenlabs) by >= 0.61 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on ElevenLabs's representative SKU for speech-synthesis without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=elevenlabs) or sustained >= 30% degraded/failed rate in verified production outcomes."],"frozenHoldoutPolicy":{"holdoutSplit":"20% frozen benchmark holdout tasks + 80% live production outcome receipts","requireCountersignReceipt":true,"requiredEvidenceTiers":["outcome_verified","reference_checked"],"minDistinctContributors":2,"antiGamingRule":"Unverified self-reports and seed/editorial rows never mutate picks or scores."},"triggers":[{"kind":"verified_outcomes_outperformance","challengerId":"cartesia","minVerifiedOutcomes":10,"requiredOutcomeMargin":0.61,"requiredWorkedRateDelta":0.15},{"kind":"verified_price_increase","providerId":"elevenlabs","maxPriceIncreasePct":25},{"kind":"live_rail_exhaustion_or_degradation","providerId":"elevenlabs","immediateOverrideUrl":"/api/decide?jtbd=speech-synthesis&exhausted=elevenlabs"}],"submissionSpec":{"falsifyEndpoint":"/api/falsify?jtbd=speech-synthesis","outcomesEndpoint":"POST /api/feedback","correctionsEndpoint":"POST /api/corrections","payloadTemplate":{"agentIdentity":"agent:<your-agent-id>","jtbdId":"speech-synthesis","providerId":"cartesia","outcome":"worked","detail":"Comparative production evaluation on speech-synthesis (n>=10 tasks) with Countersign receipt.","confidence":"high","receipt":{"countersign":{"claim_id":"cs-00000000","status":"verified","evidence_tier":"outcome_verified","counts_as_verified":true}}}}},"whatWouldChangePick":["Cartesia (cartesia) outperforms ElevenLabs (elevenlabs) by >= 0.61 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on ElevenLabs's representative SKU for speech-synthesis without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=elevenlabs) or sustained >= 30% degraded/failed rate in verified production outcomes."],"routePlan":{"jtbdId":"speech-synthesis","primary":{"providerId":"elevenlabs","name":"ElevenLabs","overall":8.27,"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.27,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"primary","reason":"Editorial Depot Pick for Text-to-speech; healthy/eligible under caller constraints."},"fallback":[{"providerId":"cartesia","name":"Cartesia","overall":7.81,"scoreBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"scoreLayers":{"editorialPrior":7.81,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Text-to-speech."},{"providerId":"openai-media","name":"OpenAI Media (Images/Audio)","overall":8.15,"scoreBand":{"low":7.6,"mid":8.2,"high":8.8,"halfWidth":0.6,"basis":"editorial_prior","display":"7.6–8.8 (editorial prior)"},"scoreLayers":{"editorialPrior":8.15,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Text-to-speech."},{"providerId":"hume","name":"Hume AI","overall":7.63,"scoreBand":{"low":7,"mid":7.6,"high":8.2,"halfWidth":0.6,"basis":"editorial_prior","display":"7.0–8.2 (editorial prior)"},"scoreLayers":{"editorialPrior":7.63,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Text-to-speech."},{"providerId":"minimax","name":"MiniMax","overall":7.83,"scoreBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"scoreLayers":{"editorialPrior":7.83,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Text-to-speech."},{"providerId":"rime","name":"Rime","overall":8.27,"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.27,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Text-to-speech."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"elevenlabs","activePrimaryId":"elevenlabs","summary":"0.00 score regret: unconstrained editorial pick satisfies all caller constraints."},"evidenceAgeDays":{"editorialScoreAgeDays":44,"pricingVerifiedAgeDays":1,"editorialPriorAsOf":"2026-09-14","pricingLastVerifiedAt":"2026-10-27"},"confidenceBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"constraintsApplied":false,"constraintBundle":{"task":null,"jtbd":"speech-synthesis","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]}},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","tie":false,"scoreGap":0.46,"decidingFactor":null,"tieNote":null,"rationale":"capability voice quality + dx.","whenNotTopPick":"Already all-in on OpenAI and quality sufficient.","skipTopPick":false,"skipReason":null,"matchedConstraints":[],"pricingSummary":"TTS/STS/voice agents; character/credit plans; telephony integrations (e.g. Twilio).","cite":"Depot Pick for speech-synthesis: elevenlabs (asOf 2026-09-14). See GET /api/jtbds/speech-synthesis + GET /api/methodology.","nextActions":[{"step":1,"title":"Inspect full JTBD + embeds","href":"/api/jtbds/speech-synthesis?embed=providers","why":"Confirm pick, runners-up, and methodology notes."},{"step":2,"title":"Quote sourced SKUs","href":"/api/quote?jtbd=speech-synthesis","why":"Depot Pick SKUs plus the cheapest sourced SKU whose unit matches this job. Does not change the pick. Does not blend input and output or borrow a chat rate for a non-chat job."},{"step":3,"title":"Open provider detail","href":"/api/providers/elevenlabs","why":"Scores, pricingNotes, strengths/weaknesses, communitySignals (claims only)."},{"step":4,"title":"Cite methodology","href":"/api/methodology","why":"Required when publishing a Depot Pick citation."},{"step":5,"title":"Grab badge SVG","href":"/api/badge?type=depot-pick&jtbd=speech-synthesis","why":"Embed in README / agent passport."},{"step":6,"title":"Post production insight","method":"POST","href":"/api/insights","why":"Unverified until curated; never auto-mutates official scores."}],"honesty":["Do not invent scores or benches.","Insights are claims until curated/reviewed; they never silently mutate official scores.","lockInRisk higher = more lock-in (worse).","normalizedUsdPerMillionTokens is set only for a single sourced token row. Otherwise null, with a machine-readable reason. Do not coerce GPU, minute, or per-1k search units.","Runners-up are not Depot Picks.","Depot overall is editorial_weighted, not Arena Elo and not an Artificial Analysis index."],"asOf":"2026-09-14","depth":{"whenNotToUse":{"text":"Already all-in on OpenAI and quality sufficient.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"cartesia","name":"Cartesia","overallForJob":7.81,"pickOverallForJob":8.27,"beatsPickOn":["pricePerformance","privacyPosture","lockInRisk"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":5.5,"runnerUpLockInRisk":4.5,"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"},{"id":"espeak-ng","name":"eSpeak NG","license":"GPL-3.0","sourceUrl":"https://raw.githubusercontent.com/espeak-ng/espeak-ng/master/COPYING"}],"migration":"Runner-up Cartesia has lower stored lock-in risk (4.5 vs 5.5, 0–10, higher = more lock-in). Self-host fallback listed for this job: Kokoro-82M, Piper, eSpeak NG.","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."}},"citation":{"text":"Agent Provider Depot (v0.12.158), Depot Pick for speech-synthesis: elevenlabs, scores as of 2026-09-14, retrieved 2026-10-28. https://getagentdepot.com/jtbds/speech-synthesis","markdown":"[Agent Provider Depot](https://getagentdepot.com/jtbds/speech-synthesis) (v0.12.158) — Depot Pick for `speech-synthesis`: **elevenlabs** (scores as of 2026-09-14, retrieved 2026-10-28)","fields":{"publisher":"Agent Provider Depot","version":"0.12.158","role":"depot_pick","jtbdId":"speech-synthesis","providerId":"elevenlabs","scoreAsOf":"2026-09-14","retrievedOn":"2026-10-28","page":"https://getagentdepot.com/jtbds/speech-synthesis","api":"https://getagentdepot.com/api/decide?jtbd=speech-synthesis"},"howToCite":"Cite Depot as an editorial, dated recommendation, not a benchmark: name the job, the Depot Pick (or runner-up), the score asOf date and the day you retrieved it, and link the job page. Format: “Agent Provider Depot (v{version}), Depot Pick for {jobId}: {providerId}, scores as of {scoreAsOf}, retrieved {retrievedOn}. {baseUrl}/jtbds/{jobId}”. Quote prices only with their own sourceUrl and asOf. If the pick's score is stale (freshness.pick.score.stale), say so."},"freshness":{"pick":{"score":{"asOf":"2026-09-14","ageDays":44,"stale":true,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-09-14","ageDays":44,"stale":true,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-27","sourceUrls":1,"sourcesReachable":1,"pricingRows":12,"pricingRowsReconfirmed":9,"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}},"scoreAsOf":"2026-09-14","editorialPriorAsOf":"2026-09-14","pricingLastVerifiedAt":"2026-10-27","pickLastReviewed":"2026-09-14","runnersUpScoreAsOf":["2026-09-14","2026-09-14","2026-09-14","2026-09-14","2026-09-14"],"contractAsOf":"2026-10-03","pricingShape":"sourced_rows","normalizedUsdPerMillionTokens":null,"normalizationStatus":"unit_mismatch","normalizationReason":"unit_mismatch"},"pricingContract":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unit_mismatch","normalizationReason":"unit_mismatch","shape":"sourced_rows","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[{"id":"elevenlabs-tts-v4","providerId":"elevenlabs","sku":"v4 Text to Speech","unit":"usd_per_1k_characters","amountUsd":0.08,"currency":"USD","sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-19","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_characters","priceSortEligible":false,"qualifier":"Price per 1K characters on the API card and every tier of the Text to Speech API table (rendered 2026-10-19). The 72%-off promo stored on 2026-10-03 ($0.022, ended Oct 12) is no longer shown. The page's ~$/minute illustration was not stored."},{"id":"elevenlabs-tts-v4-turbo","providerId":"elevenlabs","sku":"v4 Turbo Text to Speech","unit":"usd_per_1k_characters","amountUsd":0.04,"currency":"USD","sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-19","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_characters","priceSortEligible":false,"qualifier":"Price per 1K characters on the API card and every tier of the Text to Speech API table (rendered 2026-10-19). The 72%-off promo stored on 2026-10-03 ($0.011, ended Oct 12) is no longer shown. The page's ~$/minute illustration was not stored."},{"id":"elevenlabs-tts-v3","providerId":"elevenlabs","sku":"v3 Text to Speech","unit":"usd_per_1k_characters","amountUsd":0.08,"currency":"USD","sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_characters","priceSortEligible":false,"qualifier":"Price per 1K characters."},{"id":"elevenlabs-tts-v3-conversational","providerId":"elevenlabs","sku":"v3 Conversational Text to Speech","unit":"usd_per_1k_characters","amountUsd":0.04,"currency":"USD","sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_characters","priceSortEligible":false,"qualifier":"Price per 1K characters."},{"id":"elevenlabs-tts-v2-multilingual","providerId":"elevenlabs","sku":"v2 Multilingual Text to Speech","unit":"usd_per_1k_characters","amountUsd":0.08,"currency":"USD","sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_characters","priceSortEligible":false,"qualifier":"Price per 1K characters."},{"id":"elevenlabs-tts-flash-turbo","providerId":"elevenlabs","sku":"Flash / Turbo Text to Speech","unit":"usd_per_1k_characters","amountUsd":0.04,"currency":"USD","sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_characters","priceSortEligible":false,"qualifier":"Price per 1K characters."},{"id":"elevenlabs-scribe-v2","providerId":"elevenlabs","sku":"Scribe v2 speech-to-text","unit":"usd_per_hour","amountUsd":0.22,"currency":"USD","sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_hour","priceSortEligible":false,"qualifier":"Scribe v2 and Scribe v2 Medical are both $0.22 per hour on the API card. Not converted to per minute."},{"id":"elevenlabs-scribe-v2-realtime","providerId":"elevenlabs","sku":"Scribe v2 Realtime speech-to-text","unit":"usd_per_hour","amountUsd":0.39,"currency":"USD","sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_hour","priceSortEligible":false,"qualifier":"Price per hour."},{"id":"elevenlabs-scribe-entity-detection","providerId":"elevenlabs","sku":"Scribe entity detection","unit":"usd_per_hour","amountUsd":0.07,"currency":"USD","sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_hour","priceSortEligible":false,"qualifier":"Add-on per hour on the Speech to Text API table. Not the transcription rate.","sourceStatus":"unverified","sourceStatusReason":"sku_not_on_page: the rendered Speech to Text API table (2026-10-19) lists Keyterm prompting $0.050/h and Transcript editing $0.070/h; 'entity detection' is not on the page. The $0.07 column is now labelled Transcript editing, so this row is not reconfirmed.","sourceStatusCheckedOn":"2026-10-19"},{"id":"elevenlabs-scribe-keyterm","providerId":"elevenlabs","sku":"Scribe keyterm prompting","unit":"usd_per_hour","amountUsd":0.05,"currency":"USD","sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_hour","priceSortEligible":false,"qualifier":"Add-on per hour. Not the transcription rate."},{"id":"elevenlabs-speech-engine","providerId":"elevenlabs","sku":"Speech Engine","unit":"usd_per_minute","amountUsd":0.08,"currency":"USD","sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_minute","priceSortEligible":false,"qualifier":"Agents speech engine. Additional minutes $0.08. Not the per-character voice model rate."},{"id":"elevenlabs-speech-engine-burst","providerId":"elevenlabs","sku":"Speech Engine burst","unit":"usd_per_minute","amountUsd":0.16,"currency":"USD","sourceUrl":"https://elevenlabs.io/pricing/api","asOf":"2026-10-03","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_minute","priceSortEligible":false,"qualifier":"Burst pricing per minute on the Speech Engine table."}],"notesExcerpt":"TTS/STS/voice agents; character/credit plans; telephony integrations (e.g. Twilio).","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://elevenlabs.io","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"Partial coverage. Providers without a fetched SKU are omitted. See GET /api/pricing."},"links":{"jtbd":"/jtbds/speech-synthesis","jtbdApi":"/api/jtbds/speech-synthesis","leaderboard":"/api/leaderboards?jtbd=speech-synthesis","methodology":"/api/methodology","badge":"/api/badge?type=depot-pick&jtbd=speech-synthesis","decide":"/api/decide?jtbd=speech-synthesis","humanPage":"/jtbds/speech-synthesis","alternatives":"/api/alternatives?provider=elevenlabs","canonical":"/api/canonical","quote":"/api/quote?jtbd=speech-synthesis","falsify":"/api/falsify?jtbd=speech-synthesis"},"constraintBundle":{"task":null,"jtbd":"speech-synthesis","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]},"stackContext":{"host":null,"framework":null,"repo":null,"lang":null,"existing":[],"volume":null,"sender":null,"detectedFromTask":[]},"keep":null,"contextAdvice":null,"communityFeedback":{"pickOnThisJob":{"failed":0,"degraded":0,"worked":0,"insights":0,"withVerifiedReceipt":0,"failureModes":{},"latestAt":null,"note":"Agent-reported claims (unverified unless a receipt is verified by Depot's re-check). They never change scores or picks."},"outcomes":{"job":{"n":0,"worked":0,"degraded":0,"failed":0,"failureModes":{},"verifiedReports":0,"contributors":0,"excluded":{"seed_editorial":0,"test":0,"notFeedback":0},"reason":"no_submitted_outcome_reports_yet"},"pick":{"providerId":"elevenlabs","n":0,"worked":0,"degraded":0,"failed":0,"failureModes":{},"evidenceTiers":{"agent_claim":0,"self_declared":0,"reference_checked":0,"outcome_verified":0},"reason":"no_submitted_outcome_reports_yet"},"scoresMutated":false,"more":"/api/outcomes?jtbd=speech-synthesis"},"report":"POST /api/feedback {agentIdentity, outcome: failed|degraded|worked, detail, providerId, jtbdId, failureModeId?, receipt?}"}}