{"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"],"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","fr","de","it","pt"],"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"]},"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"],"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"],"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"],"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"],"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"],"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"],"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"],"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"],"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":["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"],"encodings":["linear16","mulaw"],"sample_rates":[8000,16000,22050,24000,44100,48000]}},{"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"]}},{"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"]}},{"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"],"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"],"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":["auto"],"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"],"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"]}},{"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":["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":["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"],"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"],"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"]}},{"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"]}},{"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"],"diarization":true}},{"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"],"encodings":["linear16","linear32","mulaw","alaw"],"sample_rates":[8000,16000,24000,44100,48000]},"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"]},"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"],"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"],"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"]}}]}