{"object":"list","data":[{"slug":"assemblyai/universal-3-5-pro","provider":"assemblyai","name":"AssemblyAI Universal-3.5 Pro","kind":"stt","modes":["streaming"],"pricing":{"per_session_hour_usd":0.45,"per_second_usd":0.000125},"capabilities":{"diarization":true,"word_timestamps":true,"interim_results":true,"endpointing":true,"keyword_boosting":true,"languages":["auto","multi","en","es","de","fr","pt","it","tr","nl","sv","no","da","fi","hi","vi","ar","he","ja","zh"],"encodings":["linear16","mulaw","opus","ogg-opus"],"sample_rates":[8000,16000,24000,44100,48000]},"hipaa_eligible":true},{"slug":"assemblyai/universal-streaming-english","provider":"assemblyai","name":"AssemblyAI Universal-Streaming (English)","kind":"stt","modes":["streaming"],"pricing":{"per_session_hour_usd":0.15012,"per_second_usd":0.000041700000000000004},"capabilities":{"diarization":true,"word_timestamps":true,"interim_results":true,"endpointing":true,"keyword_boosting":true,"languages":["en"],"encodings":["linear16","mulaw","opus","ogg-opus"],"sample_rates":[8000,16000,24000,44100,48000]},"hipaa_eligible":true},{"slug":"assemblyai/universal-streaming-multilingual","provider":"assemblyai","name":"AssemblyAI Universal-Streaming (Multilingual)","kind":"stt","modes":["streaming"],"pricing":{"per_session_hour_usd":0.15012,"per_second_usd":0.000041700000000000004},"capabilities":{"diarization":true,"word_timestamps":true,"interim_results":true,"endpointing":true,"keyword_boosting":true,"languages":["auto","en","es","de","fr","pt","it"],"encodings":["linear16","mulaw","opus","ogg-opus"],"sample_rates":[8000,16000,24000,44100,48000]},"hipaa_eligible":true},{"slug":"assemblyai/universal-2","provider":"assemblyai","name":"AssemblyAI Universal-2 (batch)","kind":"stt","modes":["batch"],"pricing":{"per_audio_hour_usd":0.20988,"per_second_usd":0.0000583},"capabilities":{"diarization":true,"word_timestamps":true,"keyword_boosting":true,"languages":["auto","en","es","fr","de","it","pt","nl","hi","ja","zh","fi","ko","pl","ru","tr","uk","vi"]},"hipaa_eligible":true},{"slug":"aws/transcribe","provider":"aws","name":"Amazon Transcribe Streaming","kind":"stt","modes":["streaming"],"pricing":{"per_audio_minute_usd":0.01,"minimum_usd":0.0025,"per_second_usd":0.00016666666666666666},"capabilities":{"diarization":true,"word_timestamps":true,"interim_results":true,"endpointing":true,"languages":["auto","af-ZA","sq-AL","am-ET","ar-AE","ar-SA","hy-AM","eu-ES","be-BY","bn-IN","bs-BA","my-MM","bg-BG","ca-ES","ckb-IQ","ckb-IR","zh-HK","zh-CN","zh-TW","hr-HR","cs-CZ","da-DK","nl-NL","en-US","en-GB","en-AU","en-IN","en-IE","en-NZ","en-ZA","en-AB","en-WL","et-ET","fa-IR","fa-AF","fi-FI","fr-FR","fr-CA","gl-ES","ka-GE","de-DE","de-CH","el-GR","gu-IN","ht-HT","he-IL","hi-IN","hu-HU","is-IS","id-ID","it-IT","ja-JP","jv-ID","kab-DZ","kn-IN","kk-KZ","km-KH","ko-KR","lv-LV","lt-LT","lg-IN","mk-MK","ms-MY","ml-IN","mr-IN","ne-NP","no-NO","or-IN","ps-AF","pl-PL","pt-PT","pt-BR","pa-IN","ro-RO","ru-RU","sr-RS","si-LK","sk-SK","sl-SI","so-SO","es-ES","es-MX","es-US","su-ID","sw-KE","sw-TZ","sw-UG","sv-SE","tl-PH","ta-IN","te-IN","th-TH","tr-TR","uk-UA","uz-UZ","vi-VN","cy-WL","zu-ZA"],"encodings":["linear16","ogg-opus","flac"],"sample_rates":[8000,16000,24000,44100,48000]},"hipaa_eligible":true},{"slug":"azure/fast-transcription","provider":"azure","name":"Azure AI Speech Fast Transcription","kind":"stt","modes":["batch"],"pricing":{"per_audio_hour_usd":0.36,"per_second_usd":0.00009999999999999999},"capabilities":{"word_timestamps":true,"diarization":true,"keyword_boosting":true,"languages":["auto","en-US","en-GB","en-AU","en-CA","en-IN","en-IE","en-NZ","es-ES","es-MX","es-US","es-AR","es-CO","fr-FR","fr-CA","de-DE","de-AT","de-CH","it-IT","pt-BR","pt-PT","nl-NL","nl-BE","ja-JP","ko-KR","zh-CN","zh-TW","zh-HK","ru-RU","ar-SA","ar-EG","ar-AE","hi-IN","tr-TR","pl-PL","sv-SE","da-DK","nb-NO","fi-FI","el-GR","cs-CZ","hu-HU","ro-RO","uk-UA","he-IL","th-TH","vi-VN","id-ID","ms-MY","ta-IN","te-IN"],"max_audio_seconds":18000},"hipaa_eligible":true},{"slug":"azure/speech-realtime","provider":"azure","name":"Azure Speech Realtime","kind":"stt","modes":["streaming"],"pricing":{"per_audio_hour_usd":1.0,"per_second_usd":0.0002777777777777778},"capabilities":{"interim_results":true,"word_timestamps":true,"languages":["auto","en-US","en-GB","en-AU","en-CA","en-IN","en-IE","en-NZ","es-ES","es-MX","es-US","es-AR","es-CO","fr-FR","fr-CA","de-DE","de-AT","de-CH","it-IT","pt-BR","pt-PT","nl-NL","nl-BE","ja-JP","ko-KR","zh-CN","zh-TW","zh-HK","ru-RU","ar-SA","ar-EG","ar-AE","hi-IN","tr-TR","pl-PL","sv-SE","da-DK","nb-NO","fi-FI","el-GR","cs-CZ","hu-HU","ro-RO","uk-UA","he-IL","th-TH","vi-VN","id-ID","ms-MY","ta-IN","te-IN"],"encodings":["linear16"],"sample_rates":[8000,16000],"diarization":false,"keyword_boosting":true}},{"slug":"azure/conversation-transcription","provider":"azure","name":"Azure Conversation Transcription","kind":"stt","modes":["streaming"],"pricing":{"per_audio_hour_usd":1.2,"per_second_usd":0.0003333333333333333},"capabilities":{"interim_results":true,"word_timestamps":true,"languages":["auto","en-US","en-GB","en-AU","en-CA","en-IN","en-IE","en-NZ","es-ES","es-MX","es-US","es-AR","es-CO","fr-FR","fr-CA","de-DE","de-AT","de-CH","it-IT","pt-BR","pt-PT","nl-NL","nl-BE","ja-JP","ko-KR","zh-CN","zh-TW","zh-HK","ru-RU","ar-SA","ar-EG","ar-AE","hi-IN","tr-TR","pl-PL","sv-SE","da-DK","nb-NO","fi-FI","el-GR","cs-CZ","hu-HU","ro-RO","uk-UA","he-IL","th-TH","vi-VN","id-ID","ms-MY","ta-IN","te-IN"],"encodings":["linear16"],"sample_rates":[8000,16000],"diarization":true}},{"slug":"cartesia/ink-2","provider":"cartesia","name":"Cartesia Ink-2","kind":"stt","modes":["streaming"],"pricing":{"per_audio_minute_usd":0.00648,"per_second_usd":0.000108},"capabilities":{"word_timestamps":true,"interim_results":true,"keyword_boosting":true,"languages":["en"],"encodings":["linear16","linear32","mulaw","alaw"],"sample_rates":[8000,16000,24000,44100,48000]}},{"slug":"cartesia/ink-whisper","provider":"cartesia","name":"Cartesia Ink-Whisper","kind":"stt","modes":["streaming","batch"],"pricing":{"per_audio_minute_usd":0.00216,"per_second_usd":0.000036},"capabilities":{"word_timestamps":true,"interim_results":true,"languages":["auto","af","am","ar","as","az","ba","be","bg","bn","bo","br","bs","ca","cs","cy","da","de","el","en","es","et","eu","fa","fi","fo","fr","gl","gu","ha","haw","he","hi","hr","ht","hu","hy","id","is","it","ja","jw","ka","kk","km","kn","ko","la","lb","ln","lo","lt","lv","mg","mi","mk","ml","mn","mr","ms","mt","my","ne","nl","nn","no","oc","pa","pl","ps","pt","ro","ru","sa","sd","si","sk","sl","sn","so","sq","sr","su","sv","sw","ta","te","tg","th","tk","tl","tr","tt","uk","ur","uz","vi","yi","yo","zh"],"encodings":["linear16","linear32","mulaw","alaw"],"sample_rates":[8000,16000,24000,44100,48000]}},{"slug":"cartesia/ink-2-turns","provider":"cartesia","name":"Cartesia Ink-2 (Turns)","kind":"stt","modes":["streaming"],"pricing":{"per_audio_minute_usd":0.00648,"per_second_usd":0.000108},"capabilities":{"word_timestamps":false,"interim_results":true,"endpointing":true,"keyword_boosting":true,"diarization":false,"languages":["en"],"encodings":["linear16","linear32","mulaw","alaw"],"sample_rates":[8000,16000,24000,44100,48000]}},{"slug":"deepgram/nova-3","provider":"deepgram","name":"Deepgram Nova-3","kind":"stt","modes":["streaming","batch"],"pricing":{"per_audio_minute_usd":0.0048,"per_second_usd":0.00007999999999999999},"capabilities":{"diarization":true,"word_timestamps":true,"interim_results":true,"endpointing":true,"keyword_boosting":true,"languages":["auto","multi","en","en-US","en-AU","en-GB","en-IN","en-NZ","es","es-419","fr","fr-CA","de","de-CH","hi","ru","pt","pt-BR","pt-PT","ja","it","nl","nl-BE","ar","be","bn","bs","bg","ca","zh","zh-CN","zh-TW","zh-HK","hr","cs","da","et","fi","el","gu","he","hu","id","kn","ko","lv","lt","mk","ms","mr","no","fa","pl","ro","sr","sk","sl","sv","tl","ta","te","th","tr","uk","ur","vi"],"encodings":["linear16","linear32","mulaw","alaw","opus","ogg-opus","flac"],"sample_rates":[8000,16000,24000,44100,48000]},"hipaa_eligible":true},{"slug":"deepgram/nova-3-medical","provider":"deepgram","name":"Deepgram Nova-3 Medical","kind":"stt","modes":["streaming","batch"],"pricing":{"per_audio_minute_usd":0.0048,"per_second_usd":0.00007999999999999999},"capabilities":{"diarization":true,"word_timestamps":true,"interim_results":true,"endpointing":true,"keyword_boosting":true,"languages":["en","en-US","en-GB","en-AU","en-IN","en-NZ"],"encodings":["linear16","linear32","mulaw","alaw","opus","ogg-opus","flac"],"sample_rates":[8000,16000,24000,44100,48000]},"hipaa_eligible":true},{"slug":"deepgram/nova-2","provider":"deepgram","name":"Deepgram Nova-2","kind":"stt","modes":["streaming","batch"],"pricing":{"per_audio_minute_usd":0.0048,"per_second_usd":0.00007999999999999999},"capabilities":{"diarization":true,"word_timestamps":true,"interim_results":true,"endpointing":true,"keyword_boosting":true,"languages":["auto","multi","en","en-US","en-AU","en-GB","en-NZ","en-IN","es","es-419","bg","ca","zh","zh-CN","zh-TW","zh-HK","cs","da","nl","nl-BE","et","fi","fr","fr-CA","de","de-CH","el","hi","hu","id","it","ja","ko","lv","lt","ms","no","pl","pt","pt-BR","pt-PT","ro","ru","sk","sv","th","tr","uk","vi"],"encodings":["linear16","linear32","mulaw","alaw","opus","ogg-opus","flac"],"sample_rates":[8000,16000,24000,44100,48000]},"hipaa_eligible":true},{"slug":"deepgram/flux-general-en","provider":"deepgram","name":"Deepgram Flux (English)","kind":"stt","modes":["streaming"],"pricing":{"per_audio_minute_usd":0.00648,"per_second_usd":0.000108},"capabilities":{"word_timestamps":true,"interim_results":true,"endpointing":true,"keyword_boosting":true,"diarization":false,"languages":["en"],"encodings":["linear16","linear32","mulaw","alaw","opus","ogg-opus"],"sample_rates":[8000,16000,24000,44100,48000]}},{"slug":"deepgram/flux-general-multi","provider":"deepgram","name":"Deepgram Flux (Multilingual)","kind":"stt","modes":["streaming"],"pricing":{"per_audio_minute_usd":0.0078,"per_second_usd":0.00013},"capabilities":{"word_timestamps":true,"interim_results":true,"endpointing":true,"keyword_boosting":true,"diarization":false,"languages":["multi","en","es","fr","de","hi","ru","pt","ja","it","nl"],"encodings":["linear16","linear32","mulaw","alaw","opus","ogg-opus"],"sample_rates":[8000,16000,24000,44100,48000]}},{"slug":"elevenlabs/scribe_v2_realtime","provider":"elevenlabs","name":"ElevenLabs Scribe v2 Realtime","kind":"stt","modes":["streaming"],"pricing":{"per_audio_hour_usd":0.3888,"per_second_usd":0.000108},"capabilities":{"word_timestamps":true,"interim_results":true,"endpointing":true,"keyword_boosting":true,"languages":["auto","af","am","ar","hy","as","az","be","bn","bs","bg","my","yue","ca","ceb","hr","cs","da","nl","en","et","fil","fi","fr","gl","lg","ka","de","el","gu","ha","he","hi","hu","is","ig","id","ga","it","ja","jv","kn","kk","km","ko","ku","ky","lo","lv","ln","lt","lb","mk","ms","ml","mt","zh","mi","mr","mn","ne","no","oc","or","ps","fa","pl","pt","pa","ro","ru","sr","sn","sd","sk","sl","so","es","sw","sv","ta","tg","te","th","tr","uk","ur","uz","vi","cy","wo","xh","zu"],"encodings":["linear16","mulaw"],"sample_rates":[8000,16000,22050,24000,44100,48000],"language_hints":true}},{"slug":"elevenlabs/scribe_v2","provider":"elevenlabs","name":"ElevenLabs Scribe v2 (batch)","kind":"stt","modes":["batch"],"pricing":{"per_audio_hour_usd":0.21996,"per_second_usd":0.0000611},"capabilities":{"word_timestamps":true,"diarization":true,"keyword_boosting":true,"languages":["auto","af","am","ar","hy","as","az","be","bn","bs","bg","my","yue","ca","ceb","hr","cs","da","nl","en","et","fil","fi","fr","gl","lg","ka","de","el","gu","ha","he","hi","hu","is","ig","id","ga","it","ja","jv","kn","kk","km","ko","ku","ky","lo","lv","ln","lt","lb","mk","ms","ml","mt","zh","mi","mr","mn","ne","no","oc","or","ps","fa","pl","pt","pa","ro","ru","sr","sn","sd","sk","sl","so","es","sw","sv","ta","tg","te","th","tr","uk","ur","uz","vi","cy","wo","xh","zu"]}},{"slug":"elevenlabs/scribe_v1","provider":"elevenlabs","name":"ElevenLabs Scribe v1","kind":"stt","modes":["batch"],"pricing":{"per_audio_hour_usd":0.21996,"per_second_usd":0.0000611},"capabilities":{"word_timestamps":true,"diarization":true,"keyword_boosting":true,"languages":["auto","af","am","ar","hy","as","az","be","bn","bs","bg","my","yue","ca","ceb","hr","cs","da","nl","en","et","fil","fi","fr","gl","lg","ka","de","el","gu","ha","he","hi","hu","is","ig","id","ga","it","ja","jv","kn","kk","km","ko","ku","ky","lo","lv","ln","lt","lb","mk","ms","ml","mt","zh","mi","mr","mn","ne","no","oc","or","ps","fa","pl","pt","pa","ro","ru","sr","sn","sd","sk","sl","so","es","sw","sv","ta","tg","te","th","tr","uk","ur","uz","vi","cy","wo","xh","zu"]}},{"slug":"gemini/gemini-3.5-transcribe-live","provider":"gemini","name":"Gemini 3.5 Transcribe Live","kind":"stt","modes":["streaming"],"pricing":{"per_audio_hour_usd":0.3,"per_second_usd":0.00008333333333333333},"capabilities":{"word_timestamps":false,"interim_results":true,"endpointing":false,"diarization":false,"keyword_boosting":true,"languages":["auto","af-ZA","am-ET","ar-EG","as-IN","az-AZ","be-BY","bg-BG","bn-BD","bn-IN","bs-BA","ca-ES","ceb","cmn-Hans-CN","cs-CZ","da-DK","de-DE","el-GR","en-GB","en-IN","en-US","es-419","es-US","et-EE","fa-IR","fi-FI","fil-PH","fr-FR","gl-ES","gu-IN","ha-NG","he-IL","hi-IN","hr-HR","hu-HU","hy-AM","id-ID","is-IS","it-IT","ja-JP","jv-ID","ka-GE","kea-CV","kk-KZ","km-KH","kn-IN","ko-KR","ky-KG","ln-CD","lt-LT","lv-LV","mk-MK","ml-IN","mn-MN","mr-IN","ms-MY","mt-MT","my-MM","nb-NO","ne-NP","nl-NL","or-IN","pa-Guru-IN","pa-IN","pl-PL","pt-BR","pt-PT","ro-RO","ru-RU","rup-BG","sd-Arab-IN","sk-SK","sl-SI","sr-RS","sv-SE","sw-KE","te-IN","tg-TJ","th-TH","tr-TR","uk-UA","uz-UZ","vi-VN","yue-Hant-HK"],"encodings":["linear16"],"sample_rates":[16000]}},{"slug":"google/chirp_2","provider":"google","name":"Google Chirp 2","kind":"stt","modes":["streaming"],"pricing":{"per_audio_minute_usd":0.016,"per_second_usd":0.0002666666666666667},"capabilities":{"word_timestamps":true,"interim_results":true,"endpointing":true,"languages":["auto","af-ZA","sq-AL","am-ET","ar-EG","hy-AM","rup-BG","as-IN","ast-ES","az-AZ","eu-ES","be-BY","bn-BD","bn-IN","bs-BA","bg-BG","my-MM","ca-ES","ceb-PH","ckb-IQ","cmn-Hans-CN","yue-Hant-HK","cmn-Hant-TW","hr-HR","cs-CZ","da-DK","nl-NL","en-AU","en-IN","en-GB","en-US","et-EE","fil-PH","fi-FI","fr-CA","fr-FR","ff-SN","gl-ES","lg-UG","ka-GE","de-DE","el-GR","gu-IN","ha-NG","iw-IL","hi-IN","hu-HU","is-IS","ig-NG","id-ID","ga-IE","it-IT","ja-JP","jv-ID","kea-CV","kam-KE","kn-IN","kk-KZ","km-KH","ko-KR","ky-KG","lo-LA","lv-LV","ln-CD","lt-LT","luo-KE","lb-LU","mk-MK","ms-MY","ml-IN","mt-MT","mi-NZ","mr-IN","mn-MN","ne-NP","no-NO","ny-MW","oc-FR","or-IN","om-ET","ps-AF","fa-IR","pl-PL","pt-BR","pt-PT","pa-Guru-IN","ro-RO","ru-RU","nso-ZA","sr-RS","sn-ZW","sd-IN","si-LK","sk-SK","sl-SI","so-SO","es-419","es-ES","es-US","su-ID","sw","sw-KE","sv-SE","tg-TJ","ta-IN","te-IN","th-TH","tr-TR","uk-UA","umb-AO","ur-PK","uz-UZ","vi-VN","cy-GB","wo-SN","xh-ZA","yo-NG","zu-ZA"],"encodings":["linear16"],"sample_rates":[8000,16000,24000,44100,48000]}},{"slug":"google/chirp_3","provider":"google","name":"Google Chirp 3","kind":"stt","modes":["streaming"],"pricing":{"per_audio_minute_usd":0.016,"per_second_usd":0.0002666666666666667},"capabilities":{"word_timestamps":false,"interim_results":true,"endpointing":true,"languages":["auto","af-ZA","sq-AL","am-ET","ar-DZ","ar-BH","ar-EG","ar-IQ","ar-IL","ar-JO","ar-KW","ar-LB","ar-MR","ar-MA","ar-OM","ar-XA","ar-QA","ar-SA","ar-PS","ar-SY","ar-TN","ar-AE","ar-YE","hy-AM","as-IN","ast-ES","az-AZ","eu-ES","bn-BD","bn-IN","bg-BG","my-MM","ca-ES","cmn-Hans-CN","yue-Hant-HK","cmn-Hant-TW","hr-HR","cs-CZ","da-DK","nl-BE","nl-NL","en-AU","en-HK","en-IN","en-IE","en-NZ","en-PK","en-PH","en-SG","en-GB","en-US","et-EE","fil-PH","fi-FI","fr-BE","fr-CA","fr-FR","fr-CH","gl-ES","ka-GE","de-AT","de-DE","de-CH","el-GR","gu-IN","ha-NG","iw-IL","hi-IN","hu-HU","is-IS","id-ID","it-IT","it-CH","ja-JP","jv-ID","kn-IN","kk-KZ","km-KH","rw-RW","ko-KR","ky-KG","lo-LA","lv-LV","lt-LT","lb-LU","mk-MK","ms-MY","ml-IN","mt-MT","mi-NZ","mr-IN","mn-MN","ne-NP","no-NO","or-IN","fa-IR","pl-PL","pt-BR","pt-PT","pa-Guru-IN","ro-RO","ru-RU","nso-ZA","sr-RS","sk-SK","sl-SI","st-ZA","es-AR","es-BO","es-CL","es-CO","es-CR","es-DO","es-EC","es-SV","es-GT","es-HN","es-MX","es-NI","es-PA","es-PE","es-PR","es-ES","es-US","es-UY","es-VE","sw","sw-KE","ss-Latn-ZA","sv-SE","ta-IN","te-IN","th-TH","ts-ZA","tn-Latn-ZA","tr-TR","uk-UA","ur-PK","uz-UZ","ve-ZA","vi-VN","cy-GB","wo-SN","xh-ZA","yo-NG","zu-ZA"],"encodings":["linear16"],"sample_rates":[8000,16000,24000,44100,48000]}},{"slug":"google/latest_long","provider":"google","name":"Google latest_long","kind":"stt","modes":["streaming"],"pricing":{"per_audio_minute_usd":0.016,"per_second_usd":0.0002666666666666667},"capabilities":{"word_timestamps":true,"interim_results":true,"endpointing":true,"languages":["ar-DZ","ar-BH","ar-EG","ar-IQ","ar-IL","ar-JO","ar-KW","ar-LB","ar-MR","ar-MA","ar-OM","ar-QA","ar-SA","ar-PS","ar-TN","ar-AE","ar-YE","bn-BD","bg-BG","cs-CZ","da-DK","en-AU","en-IN","en-GB","en-US","fi-FI","fr-CA","fr-FR","hu-HU","id-ID","it-IT","ja-JP","kn-IN","km-KH","ko-KR","lt-LT","mk-MK","ml-IN","mr-IN","no-NO","pl-PL","pt-BR","pt-PT","ro-RO","ru-RU","st-ZA","sv-SE","ta-IN","te-IN","th-TH","ts-ZA","tn-Latn-ZA","tr-TR","uk-UA","ve-ZA","vi-VN"],"encodings":["linear16"],"sample_rates":[8000,16000,24000,44100,48000]}},{"slug":"groq/whisper-large-v3","provider":"groq","name":"Whisper Large v3 (Groq)","kind":"stt","modes":["batch"],"pricing":{"per_audio_hour_usd":0.111,"minimum_usd":0.00031,"per_second_usd":0.000030833333333333335},"capabilities":{"word_timestamps":true,"languages":["auto","af","am","ar","as","az","ba","be","bg","bn","bo","br","bs","ca","cs","cy","da","de","el","en","es","et","eu","fa","fi","fo","fr","gl","gu","ha","haw","he","hi","hr","ht","hu","hy","id","is","it","ja","jw","ka","kk","km","kn","ko","la","lb","ln","lo","lt","lv","mg","mi","mk","ml","mn","mr","ms","mt","my","ne","nl","nn","no","oc","pa","pl","ps","pt","ro","ru","sa","sd","si","sk","sl","sn","so","sq","sr","su","sv","sw","ta","te","tg","th","tk","tl","tr","tt","uk","ur","uz","vi","yi","yo","zh"],"max_audio_seconds":0}},{"slug":"groq/whisper-large-v3-turbo","provider":"groq","name":"Whisper Large v3 Turbo (Groq)","kind":"stt","modes":["batch"],"pricing":{"per_audio_hour_usd":0.03996,"minimum_usd":0.00011,"per_second_usd":0.0000111},"capabilities":{"word_timestamps":true,"languages":["auto","af","am","ar","as","az","ba","be","bg","bn","bo","br","bs","ca","cs","cy","da","de","el","en","es","et","eu","fa","fi","fo","fr","gl","gu","ha","haw","he","hi","hr","ht","hu","hy","id","is","it","ja","jw","ka","kk","km","kn","ko","la","lb","ln","lo","lt","lv","mg","mi","mk","ml","mn","mr","ms","mt","my","ne","nl","nn","no","oc","pa","pl","ps","pt","ro","ru","sa","sd","si","sk","sl","sn","so","sq","sr","su","sv","sw","ta","te","tg","th","tk","tl","tr","tt","uk","ur","uz","vi","yi","yo","zh"]}},{"slug":"mistral/voxtral-mini-latest","provider":"mistral","name":"Mistral Voxtral Mini Transcribe","kind":"stt","modes":["batch"],"pricing":{"per_audio_minute_usd":0.003,"per_second_usd":0.00005},"capabilities":{"word_timestamps":true,"diarization":true,"keyword_boosting":true,"languages":["auto","en","zh","hi","es","ar","fr","pt","ru","de","ja","ko","it","nl"],"max_audio_seconds":10800}},{"slug":"mistral/voxtral-mini-transcribe-realtime-2602","provider":"mistral","name":"Mistral Voxtral Mini Realtime","kind":"stt","modes":["streaming"],"pricing":{"per_audio_minute_usd":0.006,"per_second_usd":0.0001},"capabilities":{"word_timestamps":false,"interim_results":true,"endpointing":true,"languages":["auto","en","zh","hi","es","ar","fr","pt","ru","de","ja","ko","it","nl"],"encodings":["linear16","linear32","mulaw","alaw"],"sample_rates":[16000]}},{"slug":"openai/gpt-realtime-whisper","provider":"openai","name":"OpenAI GPT Realtime Whisper","kind":"stt","modes":["streaming"],"pricing":{"per_audio_minute_usd":0.01698,"per_second_usd":0.000283},"capabilities":{"word_timestamps":false,"interim_results":true,"endpointing":true,"languages":["auto","af","am","ar","as","az","ba","be","bg","bn","bo","br","bs","ca","cs","cy","da","de","el","en","es","et","eu","fa","fi","fo","fr","gl","gu","ha","haw","he","hi","hr","ht","hu","hy","id","is","it","ja","jw","ka","kk","km","kn","ko","la","lb","ln","lo","lt","lv","mg","mi","mk","ml","mn","mr","ms","mt","my","ne","nl","nn","no","oc","pa","pl","ps","pt","ro","ru","sa","sd","si","sk","sl","sn","so","sq","sr","su","sv","sw","ta","te","tg","th","tk","tl","tr","tt","uk","ur","uz","vi","yi","yo","zh"],"encodings":["linear16","mulaw","alaw"],"sample_rates":[24000]}},{"slug":"openai/whisper-1","provider":"openai","name":"OpenAI Whisper-1","kind":"stt","modes":["batch"],"pricing":{"per_audio_minute_usd":0.006,"per_second_usd":0.0001},"capabilities":{"word_timestamps":true,"languages":["auto","af","am","ar","as","az","ba","be","bg","bn","bo","br","bs","ca","cs","cy","da","de","el","en","es","et","eu","fa","fi","fo","fr","gl","gu","ha","haw","he","hi","hr","ht","hu","hy","id","is","it","ja","jw","ka","kk","km","kn","ko","la","lb","ln","lo","lt","lv","mg","mi","mk","ml","mn","mr","ms","mt","my","ne","nl","nn","no","oc","pa","pl","ps","pt","ro","ru","sa","sd","si","sk","sl","sn","so","sq","sr","su","sv","sw","ta","te","tg","th","tk","tl","tr","tt","uk","ur","uz","vi","yi","yo","zh"],"max_audio_seconds":0}},{"slug":"openai/gpt-4o-transcribe","provider":"openai","name":"OpenAI GPT-4o Transcribe","kind":"stt","modes":["streaming","batch"],"pricing":{"per_audio_minute_usd":0.006,"per_second_usd":0.0001},"capabilities":{"word_timestamps":false,"languages":["auto","af","am","ar","as","az","ba","be","bg","bn","bo","br","bs","ca","cs","cy","da","de","el","en","es","et","eu","fa","fi","fo","fr","gl","gu","ha","haw","he","hi","hr","ht","hu","hy","id","is","it","ja","jw","ka","kk","km","kn","ko","la","lb","ln","lo","lt","lv","mg","mi","mk","ml","mn","mr","ms","mt","my","ne","nl","nn","no","oc","pa","pl","ps","pt","ro","ru","sa","sd","si","sk","sl","sn","so","sq","sr","su","sv","sw","ta","te","tg","th","tk","tl","tr","tt","uk","ur","uz","vi","yi","yo","zh"]}},{"slug":"openai/gpt-4o-mini-transcribe","provider":"openai","name":"OpenAI GPT-4o Mini Transcribe","kind":"stt","modes":["streaming","batch"],"pricing":{"per_audio_minute_usd":0.003,"per_second_usd":0.00005},"capabilities":{"word_timestamps":false,"languages":["auto","af","am","ar","as","az","ba","be","bg","bn","bo","br","bs","ca","cs","cy","da","de","el","en","es","et","eu","fa","fi","fo","fr","gl","gu","ha","haw","he","hi","hr","ht","hu","hy","id","is","it","ja","jw","ka","kk","km","kn","ko","la","lb","ln","lo","lt","lv","mg","mi","mk","ml","mn","mr","ms","mt","my","ne","nl","nn","no","oc","pa","pl","ps","pt","ro","ru","sa","sd","si","sk","sl","sn","so","sq","sr","su","sv","sw","ta","te","tg","th","tk","tl","tr","tt","uk","ur","uz","vi","yi","yo","zh"]}},{"slug":"openai/gpt-4o-transcribe-diarize","provider":"openai","name":"OpenAI GPT-4o Transcribe Diarize","kind":"stt","modes":["batch"],"pricing":{"per_audio_minute_usd":0.006,"per_second_usd":0.0001},"capabilities":{"word_timestamps":false,"languages":["auto","af","am","ar","as","az","ba","be","bg","bn","bo","br","bs","ca","cs","cy","da","de","el","en","es","et","eu","fa","fi","fo","fr","gl","gu","ha","haw","he","hi","hr","ht","hu","hy","id","is","it","ja","jw","ka","kk","km","kn","ko","la","lb","ln","lo","lt","lv","mg","mi","mk","ml","mn","mr","ms","mt","my","ne","nl","nn","no","oc","pa","pl","ps","pt","ro","ru","sa","sd","si","sk","sl","sn","so","sq","sr","su","sv","sw","ta","te","tg","th","tk","tl","tr","tt","uk","ur","uz","vi","yi","yo","zh"],"diarization":true}},{"slug":"palabra/asr-v1","provider":"palabra","name":"Palabra Realtime ASR v1","kind":"stt","modes":["streaming"],"pricing":{"per_audio_minute_usd":0.002,"per_second_usd":0.000033333333333333335},"capabilities":{"diarization":false,"word_timestamps":false,"interim_results":true,"endpointing":false,"keyword_boosting":false,"languages":["auto"],"encodings":["linear16","linear32","mulaw","alaw"]}},{"slug":"soniox/stt-rt-v5","provider":"soniox","name":"Soniox STT Realtime v5","kind":"stt","modes":["streaming"],"pricing":{"per_session_hour_usd":0.12,"per_second_usd":0.000033333333333333335},"capabilities":{"diarization":true,"word_timestamps":true,"interim_results":true,"endpointing":true,"keyword_boosting":true,"languages":["auto","af","sq","ar","az","eu","be","bn","bs","bg","ca","zh","hr","cs","da","nl","en","et","fi","fr","gl","de","el","gu","he","hi","hu","id","it","ja","kn","kk","ko","lv","lt","mk","ms","ml","mr","no","fa","pl","pt","pa","ro","ru","sr","sk","sl","es","sw","sv","tl","ta","te","th","tr","uk","ur","vi","cy"],"encodings":["linear16","linear32","mulaw","alaw"],"sample_rates":[8000,16000,24000,44100,48000],"language_hints":true},"hipaa_eligible":true},{"slug":"soniox/stt-async-v5","provider":"soniox","name":"Soniox STT Async v5","kind":"stt","modes":["batch"],"pricing":{"per_audio_hour_usd":0.1,"per_second_usd":0.00002777777777777778},"capabilities":{"diarization":true,"word_timestamps":true,"keyword_boosting":true,"languages":["auto","af","sq","ar","az","eu","be","bn","bs","bg","ca","zh","hr","cs","da","nl","en","et","fi","fr","gl","de","el","gu","he","hi","hu","id","it","ja","kn","kk","ko","lv","lt","mk","ms","ml","mr","no","fa","pl","pt","pa","ro","ru","sr","sk","sl","es","sw","sv","tl","ta","te","th","tr","uk","ur","vi","cy"]},"hipaa_eligible":true},{"slug":"speechmatics/enhanced","provider":"speechmatics","name":"Speechmatics Enhanced (Ursa 2)","kind":"stt","modes":["streaming","batch"],"pricing":{"per_audio_hour_usd":1.04,"per_second_usd":0.0002888888888888889},"capabilities":{"diarization":true,"word_timestamps":true,"interim_results":true,"endpointing":true,"keyword_boosting":true,"languages":["auto","ar","ba","eu","be","bn","bg","yue","ca","hr","cs","da","nl","en","eo","et","fi","fr","gl","de","el","he","hi","hu","id","ia","ga","it","ja","ko","lv","lt","ms","mt","cmn","mr","mn","no","fa","pl","pt","ro","ru","sk","sl","es","sw","sv","ta","th","tr","uk","ur","ug","vi","cy"],"encodings":["linear16","mulaw"],"sample_rates":[8000,16000,44100,48000]},"hipaa_eligible":true},{"slug":"speechmatics/standard","provider":"speechmatics","name":"Speechmatics Standard (Ursa 2)","kind":"stt","modes":["streaming","batch"],"pricing":{"per_audio_hour_usd":0.7992,"per_second_usd":0.000222},"capabilities":{"diarization":true,"word_timestamps":true,"interim_results":true,"endpointing":true,"keyword_boosting":true,"languages":["auto","ar","ba","eu","be","bn","bg","yue","ca","hr","cs","da","nl","en","eo","et","fi","fr","gl","de","el","he","hi","hu","id","ia","ga","it","ja","ko","lv","lt","ms","mt","cmn","mr","mn","no","fa","pl","pt","ro","ru","sk","sl","es","sw","sv","ta","th","tr","uk","ur","ug","vi","cy"],"encodings":["linear16","mulaw"],"sample_rates":[8000,16000,44100,48000]},"hipaa_eligible":true},{"slug":"speechmatics/melia-1","provider":"speechmatics","name":"Speechmatics Melia-1","kind":"stt","modes":["batch"],"pricing":{"per_audio_hour_usd":0.129,"per_second_usd":0.000035833333333333335},"capabilities":{"word_timestamps":true,"diarization":true,"languages":["auto","multi"],"encodings":["linear16","mulaw"]}},{"slug":"telnyx/telnyx","provider":"telnyx","name":"Telnyx STT (in-house engine)","kind":"stt","modes":["streaming"],"pricing":{"per_audio_minute_usd":0.015,"per_second_usd":0.00025},"capabilities":{"interim_results":false,"word_timestamps":false,"diarization":false,"endpointing":false,"keyword_boosting":false,"languages":["auto","af","am","ar","as","az","ba","be","bg","bn","bo","br","bs","ca","cs","cy","da","de","el","en","es","et","eu","fa","fi","fo","fr","gl","gu","ha","haw","he","hi","hr","ht","hu","hy","id","is","it","ja","jw","ka","kk","km","kn","ko","la","lb","ln","lo","lt","lv","mg","mi","mk","ml","mn","mr","ms","mt","my","ne","nl","nn","no","oc","pa","pl","ps","pt","ro","ru","sa","sd","si","sk","sl","sn","so","sq","sr","su","sv","sw","ta","te","tg","th","tk","tl","tr","tt","uk","ur","uz","vi","yi","yo","zh"]}}]}