{"id":"multilingual-stt","slug":"multilingual-stt","name":"Multilingual / code-switching speech-to-text","shortName":"Multilingual / code-switching speech-to-text","problemStatement":"Agents must transcribe 20–50+ languages or mid-utterance language switches with production accuracy — not English-only streaming.","whenNotTopPick":"English-first agent economics dominate (Deepgram) or you need OpenAI Realtime single-vendor stack.","categoryIds":["cat-media-gen","cat-inference-apis"],"depotPickProviderId":"speechmatics","depotPickRationale":"Capability on language coverage + code-switch + privacy/on-prem. PricePerf secondary to accuracy across locales.","runnersUpIds":["gladia","deepgram","assemblyai"],"weights":{"capabilityFit":0.25,"pricePerformance":0.18,"latencyReliability":0.15,"developerDx":0.15,"privacyPosture":0.1,"lockInRisk":0.07,"maturity":0.1},"methodologyNotes":"Capability on language coverage + code-switch + privacy/on-prem. PricePerf secondary to accuracy across locales.","tags":["multilingual"],"depth":{"whenNotToUse":{"text":"English-first agent economics dominate (Deepgram) or you need OpenAI Realtime single-vendor stack.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"gladia","name":"Gladia","overallForJob":7.94,"pickOverallForJob":8.24,"beatsPickOn":["pricePerformance","developerDx","lockInRisk"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":4,"runnerUpLockInRisk":3.5,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":[],"runnerUpExitSignals":[],"pickNotes":[],"selfHostFallback":[],"migration":"Runner-up Gladia has lower stored lock-in risk (3.5 vs 4, 0–10, higher = more lock-in).","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":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":2,"sourcesReachable":2,"pricingRows":3,"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":"speechmatics","slug":"speechmatics","name":"Speechmatics","tagline":"Depot pick for multilingual/production STT beyond English-first stacks. Deepgram remains default $/min…","overall":8.24},"runnersUp":[{"id":"gladia","slug":"gladia","name":"Gladia","tagline":"EU multilingual STT with a now-pinned official $/hr card. Speechmatics remains Depot multilingual pick…","overall":7.94},{"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":8.5},{"id":"assemblyai","slug":"assemblyai","name":"AssemblyAI","tagline":"Great when you need STT + audio intelligence features. Deepgram usually wins raw $/min STT.","overall":8.11}]}