Realtime streaming speech-to-text models
203 speech-to-text models from 55 providers transcribe audio as it arrives over a WebSocket or WebRTC connection, for live captions, calls and voice agents.
The cheapest published USD price is English Fast Transcription from Modulate at $0.03 per hour; 131 of 203 have a comparable price.
Of these, 3 are open weights and 2 have an announced shutdown date.
Prices are normalized: USD per hour of audio, cheapest first. Tick models to compare them side by side, or refine these filters.
Speech-to-text and realtime $ per hour of audio, log scale 239 priced
other models matches your filtersAll models by price
| Compare | Model | Price ↑ |
|---|---|---|
velma-2-stt-english-vfastEnglish Fast TranscriptionModulate, STT |
$0.03 per hour | |
velma-2-sttMultilingual TranscriptionModulate, STT |
$0.03 per hour | |
velma-2-stt-multilingual-vfastMultilingual Fast TranscriptionModulate, STT |
$0.03 per hour | |
grok-voice-transcribe-2.0Grok Voice Transcribe 2.0xAI, STT |
$0.10 per hour | |
soniox/stt-rt-v4Soniox stt-rt-v4 (via Inworld)Inworld AI, STT |
$0.12 per hour | |
soniox/stt-rt-v5Soniox stt-rt-v5 (via Inworld)Inworld AI, STT |
$0.12 per hour | |
stt-rt-v5Speech-to-Text Real-time v5Soniox, STT, ends 2026-12-15 |
$0.12 per hour | |
stt-rt-v6Speech-to-Text Real-time v6Soniox, STT |
$0.12 per hour | |
melia-1Melia 1Speechmatics, STT |
$0.12 per hour | |
ink-whisperInk WhisperCartesia, STT |
$0.13 per hour | |
ink-whisper-2025-06-04Ink Whisper (2025-06-04)Cartesia, STT |
$0.13 per hour | |
volc.bigasr.sauc.durationSeed ASR 1.0 (Streaming)BytePlus, STT |
$0.15 per hour | |
volc.seedasr.sauc.durationSeed ASR 2.0 (Streaming)BytePlus, STT |
$0.15 per hour | |
inworld/inworld-stt-1Inworld STT 1Inworld AI, STT |
$0.15 per hour | |
linden-1Linden 1Speechmatics, STT |
$0.15 per hour | |
oak-1Oak 1Speechmatics, STT |
$0.15 per hour | |
zoom-scribe-enZoom Scribe EnglishZoom AI Services, STT |
$0.15 per hour | |
zoom-scribe-multilingualZoom Scribe MultilingualZoom AI Services, STT |
$0.15 per hour | |
muse-voice-transcribe-1.0Muse Voice Transcribe 1.0Meta, STT |
$0.18 per hour | |
pulsePulseSmallest AI, STT |
$0.18 per hour | |
machineReverb ASRRev AI, STT |
$0.20 per hour | |
assemblyai/universal-3-5-proAssemblyAI Universal-3.5 Pro (via Inworld)Inworld AI, STT |
$0.21 per hour | |
scribe_v2_realtimeScribe v2 RealtimeElevenLabs, STT |
$0.22 per hour | |
scribe_v3_liveScribe v3 LiveElevenLabs, STT |
$0.22 per hour | |
standardStandardSpeechmatics, STT |
$0.23 per hour | |
horizon-universalHorizon UniversalShunya Labs, STT |
$0.23 per hour | |
gpt-transcribeGPT-TranscribeOpenAI, STT |
$0.27 per hour | |
horizon-indicHorizon IndicShunya Labs, STT |
$0.27 per hour | |
assemblyai-stt-3-7-realtimeAssemblyAI-STT-3.7-RealtimeAssemblyAI, STT |
$0.30 per hour | |
munsitMunsitMunsit, STT |
$0.30 per hour | |
munsit-en-arMunsit En-ArMunsit, STT |
$0.30 per hour | |
horizon-codeswitchHorizon Code-SwitchShunya Labs, STT |
$0.30 per hour | |
horizon-medicalHorizon MedicalShunya Labs, STT |
$0.30 per hour | |
zoom-scribe-en-proScribe API Pro High-Accuracy (English)Zoom AI Services, STT |
$0.30 per hour | |
fun-asr-realtimeFun-ASR RealtimeAlibaba Cloud Model Studio, STT |
$0.32 per hour | |
qwen-audio-3.0-asr-flash-streamingQwen-Audio 3.0 ASR Flash StreamingAlibaba Cloud Model Studio, STT |
$0.32 per hour | |
qwen3-asr-flash-realtimeQwen3-ASR Flash RealtimeAlibaba Cloud Model Studio, STT |
$0.32 per hour | |
ORACLEOracle ASROracle OCI Speech, STT |
$0.35 per hour | |
WHISPERWhisper (OCI Live Transcribe)Oracle OCI Speech, STT |
$0.35 per hour | |
transcribe-stream-1Transcribe Stream 1Fish Audio, STT, beta |
$0.36 per hour | |
voxtral-mini-transcribe-realtime-2602Voxtral Mini Transcribe Realtime (26.02)Mistral AI, STT, ends 2027-04-30 |
$0.36 per hour | |
enhancedEnhancedSpeechmatics, STT |
$0.38 per hour | |
flux-general-enFlux General EnglishDeepgram, STT |
$0.39 per hour | |
ink-2Ink 2Cartesia, STT |
$0.39 per hour | |
stepaudio-2.5-asr-streamStepAudio 2.5 ASR StreamStepFun, STT |
$0.40 per hour | |
assemblyai-stt-3-7-realtime-agentAssemblyAI-STT-3.7-Realtime-AgentAssemblyAI, STT |
$0.45 per hour | |
universal-3-6-proUniversal-3.6 ProAssemblyAI, STT |
$0.45 per hour | |
assemblyai/u3-rt-proAssemblyAI Universal-3 Pro Streaming (via Inworld)Inworld AI, STT |
$0.45 per hour | |
flux-general-multiFlux General MultilingualDeepgram, STT |
$0.47 per hour | |
voxtral-mini-transcribe-realtime-3-0Voxtral Mini Transcribe Realtime 3Mistral AI, STT, beta |
$0.48 per hour | |
async_asr_v1.0Async ASR v1.0Async, STT |
$0.50 per hour | |
MAI-Transcribe-2-StreamingAzure Speech, STT, beta |
$0.54 per hour | |
amazon-transcribe-streamingAmazon Transcribe StreamingAmazon Transcribe, STT |
$0.60 per hour | |
VoiceGain-kappaKappaVoicegain, STT |
$0.72 per hour | |
VoiceGain-rhoRhoVoicegain, STT |
$0.72 per hour | |
VoiceGain-rho-en-usRho (en-US)Voicegain, STT |
$0.72 per hour | |
azure-stt-realtimeAzure Speech-to-Text (real-time)Azure Speech, STT |
$1.00 per hour | |
kitten-asr-pro-enhancedKitten-ASR ProKittenML, STT |
$1.00 per hour | |
gpt-live-transcribeGPT-Live-TranscribeOpenAI, STT |
$1.02 per hour | |
gpt-realtime-whisperGPT-Realtime-WhisperOpenAI, STT |
$1.02 per hour | |
ar-MS_Telephonyar-MS TelephonyIBM Watson, STT |
$1.20 per hour | |
cs-CZ_Telephonycs-CZ TelephonyIBM Watson, STT |
$1.20 per hour | |
de-DEde-DE Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
de-DE_Multimediade-DE MultimediaIBM Watson, STT |
$1.20 per hour | |
de-DE_Telephonyde-DE TelephonyIBM Watson, STT |
$1.20 per hour | |
en-AUen-AU Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
en-AU_Multimediaen-AU MultimediaIBM Watson, STT |
$1.20 per hour | |
en-AU_Telephonyen-AU TelephonyIBM Watson, STT |
$1.20 per hour | |
en-GBen-GB Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
en-GB_Multimediaen-GB MultimediaIBM Watson, STT |
$1.20 per hour | |
en-GB_Telephonyen-GB TelephonyIBM Watson, STT |
$1.20 per hour | |
en-INen-IN Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
en-IN_Telephonyen-IN TelephonyIBM Watson, STT |
$1.20 per hour | |
en-USen-US Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
en-US_Multimediaen-US MultimediaIBM Watson, STT |
$1.20 per hour | |
en-US_Telephonyen-US TelephonyIBM Watson, STT |
$1.20 per hour | |
en-WW_Medical_Telephonyen-WW Medical TelephonyIBM Watson, STT, beta |
$1.20 per hour | |
es-ARes-AR Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
es-CLes-CL Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
es-COes-CO Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
es-ESes-ES Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
es-ES_Multimediaes-ES MultimediaIBM Watson, STT |
$1.20 per hour | |
es-ES_Telephonyes-ES TelephonyIBM Watson, STT |
$1.20 per hour | |
es-LA_Telephonyes-LA TelephonyIBM Watson, STT |
$1.20 per hour | |
es-MXes-MX Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
es-PEes-PE Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
fr-CAfr-CA Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
fr-CA_Multimediafr-CA MultimediaIBM Watson, STT |
$1.20 per hour | |
fr-CA_Telephonyfr-CA TelephonyIBM Watson, STT |
$1.20 per hour | |
fr-FRfr-FR Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
fr-FR_Multimediafr-FR MultimediaIBM Watson, STT |
$1.20 per hour | |
fr-FR_Telephonyfr-FR TelephonyIBM Watson, STT |
$1.20 per hour | |
hi-IN_Telephonyhi-IN TelephonyIBM Watson, STT |
$1.20 per hour | |
it-ITit-IT Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
it-IT_Multimediait-IT MultimediaIBM Watson, STT |
$1.20 per hour | |
it-IT_Telephonyit-IT TelephonyIBM Watson, STT |
$1.20 per hour | |
ja-JPja-JP Large Speech ModelIBM Watson, STT |
$1.20 per hour | |
ja-JP_Multimediaja-JP MultimediaIBM Watson, STT |
$1.20 per hour | |
ja-JP_Telephonyja-JP TelephonyIBM Watson, STT |
$1.20 per hour | |
ko-KR_Multimediako-KR MultimediaIBM Watson, STT |
$1.20 per hour |
Questions
- What is the cheapest realtime speech-to-text API?
- The lowest published USD list price is English Fast Transcription (Modulate, $0.03 per hour). Next cheapest: Multilingual Transcription (Modulate, $0.03 per hour); Multilingual Fast Transcription (Modulate, $0.03 per hour).
- Which providers offer realtime speech-to-text?
- 55 providers list 203 models: IBM Watson (51), AmiVoice (17), Tencent Cloud (15), Navana.ai (11), Inworld AI (5), Speechmatics (5), Alibaba Cloud Model Studio (5), Cartesia (4), Zoom AI Services (4), Shunya Labs (4) and 45 more.
- Is there an open-source realtime speech-to-text model?
- Yes: 3 publish their weights, including Horizon Universal, Voxtral Mini Transcribe Realtime (26.02) and OpenThai ASR Realtime. 1 of them have a licence that allows commercial use.
- Are any realtime speech-to-text models being shut down?
- 2 have an announced shutdown date: Speech-to-Text Real-time v5 (Soniox) on 2026-12-15 and Voxtral Mini Transcribe Realtime (26.02) (Mistral AI) on 2027-04-30.
- Where does this data come from?
- From each provider's own API, documentation and pricing pages, synced and reviewed in git; the latest change on this page was on 2026-11-19. Every price change, new model and shutdown is in the public changelog at /changes.
See all 203 models, with filters and sorting.
Speech-to-text by feature
- Open-source / open weights
- Realtime streaming
- Custom vocabulary
- Language detection
- PII redaction
- Profanity filter
- Punctuation
- Sentiment
- Speaker diarization
- Summarization
- Topic detection
- Translation
- Word timestamps
Speech-to-text by language
- Afrikaans
- Albanian
- Amharic
- Arabic
- Armenian
- Assamese
- Azerbaijani
- Basque
- Belarusian
- Bengali
- Bosnian
- Bulgarian
- Burmese
- Cantonese
- Catalan
- Chinese
- Croatian
- Czech
- Danish
- Dutch
- English
- Estonian
- Filipino
- Finnish
- French
- Galician
- Georgian
- German
- Greek
- Gujarati
- Hausa
- Hebrew
- Hindi
- Hungarian
- Icelandic
- Indonesian
- Irish
- Italian
- Japanese
- Javanese
- Kannada
- Kazakh
- Khmer
- Korean
- Lao
- Latvian
- Lithuanian
- Macedonian
- Malay
- Malayalam
- Maltese
- Marathi
- Mongolian
- Nepali
- Norwegian
- Odia
- Pashto
- Persian
- Polish
- Portuguese
- Punjabi
- Romanian
- Russian
- Serbian
- Sinhala
- Slovak
- Slovenian
- Somali
- Spanish
- Swahili
- Swedish
- Tagalog
- Tamil
- Telugu
- Thai
- Turkish
- Ukrainian
- Urdu
- Uzbek
- Vietnamese
- Welsh
- Yoruba
- Zulu
- ak
- ast
- ba
- bgc
- bhb
- bho
- bo
- br
- brx
- ceb
- cjy
- ckb
- doi
- eo
- ff
- fo
- fy
- gan
- gom
- hak
- haw
- hne
- hsn
- ht
- ia
- ig
- iw
- kab
- kam
- kea
- kok
- ks
- ky
- la
- lb
- lg
- ln
- luo
- mai
- mg
- mhr
- mi
- mni
- nan
- nb
- nn
- nr
- nso
- ny
- oc
- om
- rup
- rw
- sa
- sat
- sd
- sn
- ss
- st
- su
- tg
- tk
- tn
- ts
- tt
- ug
- ve
- wo
- wuu
- xh
- yi