Discover and install AI models from our curated collection
NVIDIA NeMo Parakeet TDT 0.6B v3 is an automatic speech recognition (ASR) model from NVIDIA's NeMo toolkit. Parakeet models are state-of-the-art ASR models trained on large-scale English audio data.
Links
Tags
Repository: localaiLicense: apache-2.0
Voxtral Mini 4B Realtime is a speech-to-text model from Mistral AI. It is a 4B parameter model optimized for fast, accurate audio transcription with low latency, making it ideal for real-time applications. The model uses the Voxtral architecture for efficient audio processing.
Links
Tags
Moonshine Tiny is a lightweight speech-to-text model optimized for fast transcription. It is designed for efficient on-device ASR with high accuracy relative to its size.
Links
Tags
WhisperX Tiny is a fast and accurate speech recognition model with speaker diarization capabilities. Built on OpenAI's Whisper with additional features for alignment and speaker segmentation.
Links
Tags
Repository: localaiLicense: apache-2.0
Omnilingual ASR CTC 300M (int8) is a multilingual automatic speech recognition model supporting 1,600+ languages. Based on Meta's omniASR_CTC_300M architecture (Wav2Vec2 with CTC head), quantized to int8 for efficient inference. Uses the sherpa-onnx backend with ONNX Runtime.
Links
Tags
Repository: localaiLicense: apache-2.0
Streaming English ASR: sherpa-onnx zipformer transducer (int8, chunk-16 left-128). Low-latency real-time transcription with endpoint detection via sherpa-onnx's online recognizer. English-only; for multilingual offline ASR see omnilingual-0.3b-ctc-q8-sherpa.
Links
Tags

VibeVoice ASR 7B (C++ / GGML, Q4_K) - long-form speech-to-text with speaker diarization. Returns per-speaker JSON segments with start/end timestamps. English-only. ~10 GB download.
Links
Tags
Hybrid TDT+CTC FastConformer, 110M. F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
Repository: localaiLicense: cc-by-4.0
Cache-aware streaming RNNT FastConformer with end-of-utterance (EOU) detection, 120M. Use with streaming transcription. F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
CTC FastConformer, 0.6B. F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
RNNT FastConformer, 0.6B. F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
TDT FastConformer, 0.6B (v2). F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
TDT FastConformer, 0.6B (v3, multilingual). F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
CTC FastConformer, 1.1B. F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
RNNT FastConformer, 1.1B. F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
TDT FastConformer, 1.1B. F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
Hybrid TDT+CTC FastConformer, 1.1B. F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
Repository: localaiLicense: other
Multilingual (40+ locales), prompt-conditioned, cache-aware streaming FastConformer RNN-T, 0.6B. Q8_0 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo). Byte-identical to NeMo at WER 0 offline and streaming, about 2.5x faster than NeMo on CPU with no GPU. Select a language with the request "language" field (for example en, de, es, ja-JP), or leave it empty for automatic detection. License OpenMDW-1.1.
Links
Tags
NVIDIA Parakeet TDT 0.6B v3 (FastConformer + Token-and-Duration Transducer), 25-language ASR. Runs via the CrispASR backend. Default GGUF size ~467 MB.
Links
Tags
NVIDIA Parakeet TDT 0.6B v2 (FastConformer + TDT), English-only ASR. Runs via the CrispASR backend. Default GGUF size ~468 MB.
Links
Tags
NVIDIA Parakeet TDT 0.6B Japanese ASR (F16 default; Q4_K is quantisation-sensitive for this model). Runs via the CrispASR backend. Default GGUF size ~1.24 GB.
Links
Tags