Model catalog
Speech-to-Text Model Leaderboard
This speech-to-text leaderboard compares the available benchmark ranking, score status, per-minute pricing and streaming capabilities without combining unlike evaluations.
Data as of 2026-08-17
Speech-to-Text Leaderboard Models
Browse the speech-to-text leaderboard ranking alongside the full catalog. Models without enough comparable benchmark evidence remain unscored.
Sort by
Model | LLMBoard score | Input -> output | Native price | Provider | Context | Released |
|---|
| ModelAUARK-ASR-3BAudio8 | LLMBoard score70.8 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOTMOSS-Transcribe-preview-2BOpenmoss Team | LLMBoard score70.1 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOTMOSS-Transcribe-DiarizeOpenmoss Team | LLMBoard score69.4 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelCOcohere-transcribe-03-2026Coherelabs | LLMBoard score68.7 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAUARK-ASR-0.6BAudio8 | LLMBoard score68.0 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSOZipformer-cr-ctc-transducer-XL-290MSoundsgoodai | LLMBoard score67.3 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAC | LLMBoard score66.5 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score65.8 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score64.4 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelKYstt-2.6b-enKyutai | LLMBoard score63.7 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAC | LLMBoard score63.0 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score62.3 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMAmoonshine-streaming-mediumMoonshine Ai | LLMBoard score61.6 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSOZipformer-transducer-XL-290MSoundsgoodai | LLMBoard score60.9 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score60.2 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelZA | LLMBoard score59.1 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAUAudio8-ASR-0.1BAudio8 | LLMBoard score59.1 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMIVoxtral-Mini-3B-2507Mistralai | LLMBoard score58.1 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score57.4 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score56.0 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score55.4 | Input -> outputaudio -> text | Native price$0.0007 / minute | ProviderGroq | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSPSpeechmatics EnhancedSpeechmatics | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMA | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGLSolaria-1Gladia | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSMSmallest AI Pulse ProSmallest.ai | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
ModelAM Nova 2 ProAmazon | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelST | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAL | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAS | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAL | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSOSoniox V4Soniox | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMA | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelEL | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAS | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelCO | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSMSmallest AI PulseSmallest.ai | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMOModulate STT Batch English VFastModulate | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAS | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelXA | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSPMeliaSpeechmatics | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelREResonant-1Reson8 | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGLSolaria-3Gladia | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAMAmazon TranscribeAmazon | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelTHInkling (256K)Thinkingmachines | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSOSoniox v5 AsyncSoniox | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score55.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelDWdistil-large-v3.5Distil Whisper | LLMBoard score55.3 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score54.6 | Input -> outputaudio -> text | Native price$0.0018 / minute | ProviderGroq | ContextN/A | ReleasedN/A |
| ModelESowsm_ctc_v4_1BEspnet | LLMBoard score54.6 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score53.2 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score52.9 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score52.5 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score51.8 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score51.1 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score49.9 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMAmoonshine-streaming-smallMoonshine Ai | LLMBoard score49.6 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score48.9 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score48.2 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelESowsm_ctc_v3.1_1BEspnet | LLMBoard score47.5 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score46.8 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSPasr-conformer-loquaciousSpeechbrain | LLMBoard score46.1 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score45.7 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score45.4 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAAniagara-38m-batch.enAbr Ai | LLMBoard score44.7 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score44.0 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score43.3 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMAmoonshine-baseMoonshine Ai | LLMBoard score42.6 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score41.9 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAAniagara-19m-batch.enAbr Ai | LLMBoard score41.2 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score40.5 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMAmoonshine-streaming-tinyMoonshine Ai | LLMBoard score39.8 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMAmoonshine-tinyMoonshine Ai | LLMBoard score39.1 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score38.4 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSPasr-wav2vec2-librispeechSpeechbrain | LLMBoard score37.7 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAwav2vec2-large-960h-lv60-selfFacebook | LLMBoard score37.0 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAmms-1b-allFacebook | LLMBoard score36.3 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAhubert-xlarge-ls960-ftFacebook | LLMBoard score35.6 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAhubert-large-ls960-ftFacebook | LLMBoard score34.9 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelDE | LLMBoard score34.7 | Input -> outputaudio -> text | Native price$0.007 / minute | ProviderDeepgram | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score34.7 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAMNova 2 OmniAmazon | LLMBoard score34.7 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score34.7 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSPSpeechmatics StandardSpeechmatics | LLMBoard score34.7 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score34.7 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGRGradium Speech-to-TextGradium | LLMBoard score34.7 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAL | LLMBoard score34.7 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score34.7 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelRARev AIRev AI | LLMBoard score34.7 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAL | LLMBoard score34.7 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAwav2vec2-large-robust-ft-libri-960hFacebook | LLMBoard score34.2 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAdata2vec-audio-large-960hFacebook | LLMBoard score33.5 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAwav2vec2-conformer-rope-large-960h-ftFacebook | LLMBoard score32.8 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAwav2vec2-conformer-rel-pos-large-960h-ftFacebook | LLMBoard score32.0 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAwav2vec2-large-960hFacebook | LLMBoard score31.3 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAdata2vec-audio-base-960hFacebook | LLMBoard score30.6 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAwav2vec2-base-960hFacebook | LLMBoard score29.9 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score29.4 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAmms-1b-fl102Facebook | LLMBoard score29.2 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAS | LLMBoard scoreN/A | Input -> outputaudio -> text | Native price$0.009 / minute | ProviderAssemblyai | ContextN/A | ReleasedN/A |
| ModelAS | LLMBoard scoreN/A | Input -> outputaudio -> text | Native price$0.009 / minute | ProviderAssemblyai | ContextN/A | ReleasedN/A |
| ModelAS | LLMBoard scoreN/A | Input -> outputaudio -> text | Native price$0.009 / minute | ProviderAssemblyai | ContextN/A | ReleasedN/A |
| ModelCA | LLMBoard scoreN/A | Input -> outputaudio -> text | Native price$0.0022 / minute | ProviderCartesia | ContextN/A | ReleasedN/A |
| ModelDE | LLMBoard scoreN/A | Input -> outputaudio -> text | Native price$0.007 / minute | ProviderDeepgram | ContextN/A | ReleasedN/A |
| ModelDE | LLMBoard scoreN/A | Input -> outputaudio -> text | Native price$0.007 / minute | ProviderDeepgram | ContextN/A | ReleasedN/A |
| ModelFA | LLMBoard scoreN/A | Input -> outputaudio -> text | Native price$0.0018 / minute | ProviderFireworks | ContextN/A | ReleasedN/A |
| ModelFA | LLMBoard scoreN/A | Input -> outputaudio -> text | Native price$0.0007 / minute | ProviderFireworks | ContextN/A | ReleasedN/A |
| ModelMA | LLMBoard scoreN/A | Input -> outputaudio -> text | Native price$0.067 / minute | ProviderMistral | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard scoreN/A | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
This leaderboard uses evaluation and benchmark evidence only for scores. Price, context and model specifications remain separate from the ranking.
Leaderboard overview
Models121
Vendors38
Scored models111
Ranking status111 provisional
Lowest listed native priceWhisper V3 Turbo$0.0007 / minute via Fireworks
Models12138 vendors
Multimodal inputs0Products accepting more than one input modality
Vendor catalog mix
121 modelsSpeech-to-Text Leaderboard Pricing
Use price as context for the leaderboard, not as part of its benchmark ranking. Each listing keeps its original unit.
Speech-to-Text Input and Output Modalities
Compare input and output support alongside the leaderboard; modality support does not change the benchmark ranking.
ModelIn: textIn: imageIn: audioIn: videoOut: textOut: imageOut: audioOut: video
About Speech-to-Text Model Leaderboard
How does this speech-to-text leaderboard work?
111 models currently have a domain-specific LLMBoard score. The leaderboard ranking uses matched benchmark evidence, while coverage and provisional status identify incomplete evidence.
How are prices displayed?
Prices retain the unit returned by the catalog, such as per image, per second, per minute or per million characters. They are never shown as token prices.
Why can a model have no price?
Some models do not have a current price listing in their native billing unit.