Models

• gpt-4o-transcribe audio openai
  16K ctx
• gpt-4o-transcribe-diarize audio openai
  16K ctx
• gpt-audio audio openai
  128K ctx
• gpt-audio-1.5 audio openai
  128K ctx
• gpt-audio-2025-08-28 audio openai
  128K ctx
• gpt-audio-mini audio openai
  128K ctx
• gpt-audio-mini-2025-10-06 audio openai
  128K ctx
• gpt-audio-mini-2025-12-15 audio openai
  128K ctx
• griko/gender_cls_svm_ecapa_voxceleb audio griko
• hexgrad/Kokoro-82M audio hexgrad
• hexgrad/Kokoro-82M-v1.1-zh audio hexgrad
• ibm-granite/granite-4.0-1b-speech audio ibm-granite
• ibm-granite/granite-speech-3.3-2b audio ibm
• ibm-granite/granite-speech-4.1-2b audio ibm
• imvladikon/wav2vec2-xls-r-300m-hebrew audio imvladikon
• indonesian-nlp/wav2vec2-indonesian-javanese-sundanese audio indonesian-nlp
• isaiahbjork/orpheus-3b-0.1-ft-Q4_K_M-GGUF audio isaiahbjork
• ivrit-ai/pyannote-speaker-diarization-3.1 audio ivrit-ai
• jakeBland/wav2vec-vm-finetune audio jakeBland
• jbetker/wav2vec2-large-robust-ft-libritts-voxpopuli audio jbetker
• jihedjabnoun/wavlm-base-emotion audio jihedjabnoun
• jonatasgrosman/wav2vec2-large-xlsr-53-arabic audio jonatasgrosman
• jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn audio jonatasgrosman
• jonatasgrosman/wav2vec2-large-xlsr-53-dutch audio jonatasgrosman
• jonatasgrosman/wav2vec2-large-xlsr-53-finnish audio jonatasgrosman
• jonatasgrosman/wav2vec2-large-xlsr-53-german audio jonatasgrosman
• jonatasgrosman/wav2vec2-large-xlsr-53-greek audio jonatasgrosman
• jonatasgrosman/wav2vec2-large-xlsr-53-hungarian audio jonatasgrosman
• jonatasgrosman/wav2vec2-large-xlsr-53-japanese audio jonatasgrosman
• jonatasgrosman/wav2vec2-large-xlsr-53-persian audio jonatasgrosman
• jonatasgrosman/wav2vec2-large-xlsr-53-polish audio jonatasgrosman
• jonatasgrosman/wav2vec2-large-xlsr-53-portuguese audio jonatasgrosman
• jonatasgrosman/wav2vec2-large-xlsr-53-russian audio jonatasgrosman
• jonatasgrosman/wav2vec2-xls-r-1b-portuguese audio jonatasgrosman
• k2-fsa/OmniVoice audio k2-fsa
• kenpath/svara-tts-v1 audio kenpath
• kingabzpro/wav2vec2-large-xls-r-300m-Urdu audio kingabzpro
• kotoba-tech/kotoba-whisper-v2.2 audio kotoba-tech
• kresnik/wav2vec2-large-xlsr-korean audio kresnik
• kyutai/mimi audio kyutai
• kyutai/tts-0.75b-en-public audio kyutai
• kyutai/tts-1.6b-en_fr audio kyutai
• lab260/AASIST3 audio lab260
• m-a-p/MERT-v1-330M audio m-a-p
• m-a-p/MERT-v1-95M audio m-a-p
• maya-research/Veena audio maya-research
• microsoft/VibeVoice-1.5B audio microsoft
• microsoft/VibeVoice-ASR audio microsoft
• microsoft/VibeVoice-Realtime-0.5B audio microsoft
• microsoft/speecht5_asr audio microsoft