AI Model Catalogue

Open-source qwen2-vl-audio model from mayakd — available for download and self-hosting on Hugging Face.

Open-source stt_ar_fastconformer_casablanca_nadi model from mohamedgomaa30 — available for download and self-hosting on Hugging Face.

Open-source mms-mos-finetuned model from uriath — available for download and self-hosting on Hugging Face.

Open-source whisper-tiny-yoruba model from eyedol — available for download and self-hosting on Hugging Face.

Open-source whisper-base-ar-quran-mix-norm model from deepdml — available for download and self-hosting on Hugging Face.

Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalize to many datasets and domains without the need for fine-tuning. This is the English-only version of the Whisper Tiny model which was trained on the task of speech recognition.

Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation.

Aura is a context-aware text-to-speech (TTS) model that applies natural pacing, expressiveness, and fillers based on the context of the provided text. The quality of your text input directly impacts the naturalness of the audio output.

Aura-2 is a context-aware text-to-speech (TTS) model that applies natural pacing, expressiveness, and fillers based on the context of the provided text. The quality of your text input directly impacts the naturalness of the audio output.

MeloTTS is a high-quality multi-lingual text-to-speech library by MyShell.ai.

Aura-2 is a context-aware text-to-speech (TTS) model that applies natural pacing, expressiveness, and fillers based on the context of the provided text. The quality of your text input directly impacts the naturalness of the audio output.

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.

Flux is the first conversational speech recognition model built specifically for voice agents.

An open source, community-driven, native audio turn detection model in 2nd version

Transcribe audio using Deepgram’s speech-to-text model

Open-source stable-audio-open-1.0 model from stabilityai — available for download and self-hosting on Hugging Face.

Open-source stable-audio-open-small model from stabilityai — available for download and self-hosting on Hugging Face.

Open-source overlapped-speech-detection model from pyannote — available for download and self-hosting on Hugging Face.

Open-source whisper-medium model from openai — available for download and self-hosting on Hugging Face.

Open-source wav2vec2-xls-r-300m-cv7-turkish model from mpoyraz — available for download and self-hosting on Hugging Face.

Open-source wav2vec2-large-xlsr-open-brazilian-portuguese-v2 model from lgris — available for download and self-hosting on Hugging Face.

Open-source distil-whisper-large-v3-ptbr model from freds0 — available for download and self-hosting on Hugging Face.

Open-source wav2vec2-large-xls-r-300m-Urdu model from kingabzpro — available for download and self-hosting on Hugging Face.

Open-source faster-whisper-base model from systran — available for download and self-hosting on Hugging Face.

Open-source wav2vec2-large-xlsr-53-greek model from jonatasgrosman — available for download and self-hosting on Hugging Face.

Open-source reverb-diarization-v1 model from revai — available for download and self-hosting on Hugging Face.

Open-source parakeet-tdt-0.6b-v3 model from mlx-community — available for download and self-hosting on Hugging Face.

Open-source parakeet-tdt-0.6b-v3-coreml model from fluidinference — available for download and self-hosting on Hugging Face.

Open-source wav2vec2-large-xlsr-53-telugu model from anuragshas — available for download and self-hosting on Hugging Face.

Open-source Qwen3-ASR-0.6B model from qwen — available for download and self-hosting on Hugging Face.

Open-source faster-whisper-small model from systran — available for download and self-hosting on Hugging Face.

Open-source parakeet-tdt-0.6b-v3 model from nvidia — available for download and self-hosting on Hugging Face.

Open-source wav2vec2-base-960h model from facebook — available for download and self-hosting on Hugging Face.

Open-source Voxtral-Mini-4B-Realtime-2602 model from mistralai — available for download and self-hosting on Hugging Face.