{"data":[{"id":"openai-whisper","name":"whisper","display_name":"Whisper","description":"A general-purpose automatic speech recognition model trained on diverse multilingual audio, supporting transcription and translation tasks.","creator":"openai","family":"whisper","tier":"","version":"1","type":"speech-to-text","size_in_bn":null,"modalities":{"input":["audio"],"output":["text"]},"context_window":null,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2022-09-21","earliest_deprecation_date":"2026-12-15","deprecated":false,"has_pricing":true,"provider_count":5,"ids":["@cf/openai/whisper","azure/whisper-1","deepgram/whisper","openai-whisper","openai/whisper-1","whisper-1"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-25 08:02:27"},{"id":"mistral-voxtral-small","name":"voxtral-small","display_name":"Voxtral Small 24B","description":"A 24B-parameter audio-language model from Mistral built on Mistral Small 3, excelling at speech transcription, translation, and audio understanding.","creator":"mistral","family":"voxtral","tier":"small","version":null,"type":"speech-to-text","size_in_bn":null,"modalities":{"input":["audio","text"],"output":["text"]},"context_window":128000,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Mistral","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-10-30","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["mistral-voxtral-small","mistral.voxtral-small-24b-2507","mistralai/voxtral-small-24b-2507","mistralai/Voxtral-Small-24B-2507","scaleway/mistralai/voxtral-small-24b-2507","voxtral-small-2507","voxtral-small-latest"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-25 08:02:27"},{"id":"openai-gpt-4o-mini-transcribe","name":"gpt-4o-mini-transcribe","display_name":"GPT-4o mini Transcribe","description":"A speech-to-text ASR model built on GPT-4o mini, offering improved word error rate and multilingual audio transcription accuracy.","creator":"openai","family":"gpt","tier":"mini","version":"4o","type":"speech-to-text","size_in_bn":null,"modalities":{"input":["audio","text"],"output":["text"]},"context_window":16000,"max_output_tokens":2000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2025-03-20","earliest_deprecation_date":"2027-01-20","deprecated":false,"has_pricing":true,"provider_count":3,"ids":["azure/gpt-4o-mini-transcribe","gpt-4o-mini-transcribe","gpt-4o-mini-transcribe-2025-03-20","gpt-4o-mini-transcribe-2025-12-15","openai-gpt-4o-mini-transcribe","openai/gpt-4o-mini-transcribe"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-25 08:02:27"},{"id":"openai-gpt-4o-transcribe","name":"gpt-4o-transcribe","display_name":"GPT-4o Transcribe","description":"A speech-to-text ASR model powered by GPT-4o that delivers improved word error rate and language recognition over earlier Whisper models.","creator":"openai","family":"gpt","tier":"","version":"4o","type":"speech-to-text","size_in_bn":null,"modalities":{"input":["audio","text"],"output":["text"]},"context_window":16000,"max_output_tokens":2000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2024-03-13","earliest_deprecation_date":"2026-10-15","deprecated":false,"has_pricing":true,"provider_count":3,"ids":["azure/gpt-4o-transcribe","gpt-4o-transcribe","openai-gpt-4o-transcribe","openai/gpt-4o-transcribe"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-25 08:02:27"},{"id":"openai-gpt-realtime-whisper","name":"gpt-realtime-whisper","display_name":"GPT Realtime Whisper","description":"A streaming speech-to-text model optimized for low-latency transcript delivery from live audio, tailored for real-time applications requiring fine-tuned transcription control.","creator":"openai","family":"gpt","tier":"","version":null,"type":"speech-to-text","size_in_bn":null,"modalities":{"input":["audio","text"],"output":["text"]},"context_window":16000,"max_output_tokens":2000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-09","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2026-05-07","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["azure/gpt-realtime-whisper","gpt-realtime-whisper","openai-gpt-realtime-whisper","openai/gpt-realtime-whisper"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-25 08:02:27"},{"id":"openai-whisper-3-large-turbo","name":"whisper-3-large-turbo","display_name":"Whisper 3 Large Turbo","description":"A faster, distilled variant of Whisper Large V3 that maintains strong multilingual ASR accuracy with reduced inference latency.","creator":"openai","family":"whisper","tier":"","version":"3","type":"speech-to-text","size_in_bn":0.809,"modalities":{"input":["audio"],"output":["text"]},"context_window":null,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["@cf/openai/whisper-large-v3-turbo","groq/whisper-large-v3-turbo","huggingface-asr-whisper-large-v3-turbo","openai-whisper-3-large-turbo","openai/whisper-large-v3-turbo","watsonx/whisper-large-v3-turbo"],"hf_likes":3012,"hf_downloads":7277395,"hf_downloads_all_time":83858224,"hf_trending_score":10,"updated_at":"2026-08-25 08:02:27"},{"id":"deepgram-nova-3","name":"nova-3","display_name":"Nova 3","description":"Deepgram's third-generation Nova ASR model with improved accuracy and broader language support for general transcription.","creator":"deepgram","family":"nova","tier":"","version":"3","type":"speech-to-text","size_in_bn":null,"modalities":{"input":["audio"],"output":["text"]},"context_window":null,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["@cf/deepgram/nova-3","deepgram-nova-3","deepgram/nova-3"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-25 08:02:27"},{"id":"mistral-voxtral-mini","name":"voxtral-mini","display_name":"Voxtral Mini 3B","description":"A compact 3B-parameter audio-language model from Mistral capable of speech transcription and audio understanding in a small footprint.","creator":"mistral","family":"voxtral","tier":"mini","version":null,"type":"speech-to-text","size_in_bn":null,"modalities":{"input":["audio","text"],"output":["text"]},"context_window":128000,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-12-02","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["mistral-voxtral-mini","mistral.voxtral-mini-3b-2507","mistral/voxtral-mini-2602","mistralai/Voxtral-Mini-3B-2507","voxtral-mini-2507","voxtral-mini-2602","voxtral-mini-latest"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-25 08:02:27"},{"id":"openai-gpt-4o-transcribe-diarize","name":"gpt-4o-transcribe-diarize","display_name":"GPT-4o Transcribe Diarize","description":"An ASR model built on GPT-4o with built-in speaker diarization, associating audio segments with distinct speakers in multi-party conversations.","creator":"openai","family":"gpt","tier":"","version":"4o","type":"speech-to-text","size_in_bn":null,"modalities":{"input":["audio","text"],"output":["text"]},"context_window":16000,"max_output_tokens":2000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":"2027-04-15","deprecated":false,"has_pricing":true,"provider_count":2,"ids":["azure/gpt-4o-transcribe-diarize","gpt-4o-transcribe-diarize","openai-gpt-4o-transcribe-diarize"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-25 08:02:27"},{"id":"assemblyai","name":"assemblyai","display_name":"AssemblyAI","description":"AssemblyAI's core audio transcription model offering accurate speech-to-text conversion for a wide range of audio content.","creator":"assemblyai","family":"assemblyai","tier":"","version":null,"type":"speech-to-text","size_in_bn":null,"modalities":{"input":["audio"],"output":["text"]},"context_window":null,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["assemblyai","assemblyai/nano"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-25 08:02:27"}],"meta":{"updated_at":"","request_id":"b762c1d8-4a69-4834-89cb-b9503f82348d","execution_ms":12}}