Filter by type:
Filter by tags:
vits-streaming-assistant
English voice assistant preset: Silero VAD, Parakeet TDT 0.6B v3, Qwen3
0.6B chat, and VITS-LJS English single-speaker TTS through sherpa-onnx.
Buffers streamed LLM output into clauses and emits audio progressively.
Each clause starts a separate synthesis; this is not native incremental
text input. This installs only the pipeline configuration. First install
silero-vad-ggml, parakeet-cpp-tdt-0.6b-v3, qwen3-0.6b, and vits-ljs-sherpa.
WebRTC also needs the opus backend. No browser or hardware performance
is established by this preset.
Repository: localaiLicense: mit
piper-streaming-assistant
English voice assistant preset: Silero VAD, Parakeet TDT 0.6B v3, Qwen3
0.6B chat, and Piper Amy US English TTS through piper.
Buffers streamed LLM output into clauses and emits audio progressively.
Each clause starts a separate synthesis; this is not native incremental
text input. This installs only the pipeline configuration. First install
silero-vad-ggml, parakeet-cpp-tdt-0.6b-v3, qwen3-0.6b, and voice-en-us-amy-low.
WebRTC also needs the opus backend. No browser or hardware performance
is established by this preset.
Repository: localaiLicense: mit
qwen3-streaming-assistant
English voice assistant preset: Silero VAD, Parakeet TDT 0.6B v3, Qwen3
0.6B chat, and Qwen3-TTS 0.6B CustomVoice with Ryan's voice. Streams LLM
text into one persistent TTS session while audio is emitted.
This installs only the pipeline configuration. First install the separate
gallery models silero-vad-ggml, parakeet-cpp-tdt-0.6b-v3, qwen3-0.6b, and
qwen3-tts-cpp-customvoice. Pin its variant to qwen3-tts-cpp-customvoice
for Q8. WebRTC also needs the opus backend.
Requires a LocalAI build with incremental Qwen3-TTS input support.
CPU synthesis may be slower than playback; GPU and browser performance
are not established by this preset.
Repository: localaiLicense: mit
parakeet-cpp-tdt_ctc-110m
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.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-realtime_eou_120m-v1
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.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-ctc-0.6b
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.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-rnnt-0.6b
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.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-tdt-0.6b-v2
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.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-tdt-0.6b-v3
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.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-phonon-2.5-f16
Phonon 2.5, F16: a multilingual speech recognition model for 25 European languages, by Fermion Research. F16 file, full precision, about 1.4 GB.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-phonon-2.5-q8_0
Phonon 2.5, Q8_0: a multilingual speech recognition model for 25 European languages, by Fermion Research. Q8_0 quantized file, about 940 MB.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-phonon-2.5-q4_k
Phonon 2.5, Q4_K: a multilingual speech recognition model for 25 European languages, by Fermion Research. Q4_K quantized file, about 675 MB, the smallest of the regular builds.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-phonon-2.5-packed
Phonon 2.5, PACKED: a multilingual speech recognition model for 25 European languages, by Fermion Research. Packed weights, about 240 MB, the smallest file. It runs on the CPU only, because the GPU route for packed files is not in this build. For a GPU, use the f16, q8_0 or q4_k entry instead.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-phonon-2.5-english-f16
Phonon 2.5 English, F16: the English-only speech recognition model of the Phonon 2.5 family, by Fermion Research. F16 file, full precision, about 1.4 GB.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-phonon-2.5-english-q8_0
Phonon 2.5 English, Q8_0: the English-only speech recognition model of the Phonon 2.5 family, by Fermion Research. Q8_0 quantized file, about 940 MB.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-phonon-2.5-english-q4_k
Phonon 2.5 English, Q4_K: the English-only speech recognition model of the Phonon 2.5 family, by Fermion Research. Q4_K quantized file, about 675 MB, the smallest of the regular builds.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-phonon-2.5-english-packed
Phonon 2.5 English, PACKED: the English-only speech recognition model of the Phonon 2.5 family, by Fermion Research. Packed weights, about 240 MB, the smallest file. It runs on the CPU only, because the GPU route for packed files is not in this build. For a GPU, use the f16, q8_0 or q4_k entry instead.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-ctc-1.1b
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.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-rnnt-1.1b
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.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-tdt-1.1b
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.
Repository: localaiLicense: cc-by-4.0
parakeet-cpp-tdt_ctc-1.1b
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.
Repository: localaiLicense: cc-by-4.0
Page 1