Verified Story Studio creative-audio models and runtimes for Vox Jot.
Kimani James
IrieDinamik
AI & ML interests
None yet
Recent Activity
updated a model 21 days ago
IrieDinamik/vox-jot-models updated a model about 1 month ago
IrieDinamik/vox-jot-ocr-runtime updated a model about 2 months ago
IrieDinamik/vox-jot-releasesOrganizations
None yet
Public managed runtime for Vox Jot file ASR, diarization, Polyvoice routing, and emotion analysis.
Curated speaker diarization and isolation models verified for Vox Jot file transcription.
-
pyannote/speaker-diarization-community-1
Automatic Speech Recognition • Updated • 5.1M • 3.72k -
pyannote/speaker-diarization-3.1
Automatic Speech Recognition • Updated • 6.92M • 4.85k -
BUT-FIT/diarizen-wavlm-large-s80-md-v2
Voice Activity Detection • Updated • 1.55k • 27 -
nvidia/diar_sortformer_4spk-v1
Automatic Speech Recognition • 0.1B • Updated • 101k • 163
Curated on-device OCR models verified for Vox Jot. Image-to-text and document scanning models optimized for local inference on-device.
Curated on-device TTS models verified for Vox Jot speech synthesis. Ranked: Fastest → Balanced → Best Quality → Voice Cloning. MIT/Apache licensed.
Candidate on-device TTS models under evaluation for Vox Jot. Models here are not ranked or verified until full Vox Jot benchmark suites pass.
Machine Learning Models
Curated file-transcription ASR models verified for Vox Jot. File/audio engines, not live dictation hot path.
-
ibm-granite/granite-speech-4.1-2b
Automatic Speech Recognition • 2B • Updated • 180k • 168 -
CohereLabs/cohere-transcribe-03-2026
Automatic Speech Recognition • 2B • Updated • 93.7k • • 1.23k -
Systran/faster-whisper-large-v3
Automatic Speech Recognition • Updated • 1.47M • 705 -
mlx-community/nemotron-3.5-asr-streaming-0.6b
Automatic Speech Recognition • 0.6B • Updated • 1.48k • 18
Curated on-device LLM/GGUF models verified for Vox Jot. Small, fast instruct models optimized for local inference on-device.
-
IrieDinamik/LiquidAI-LFM2.5-Audio-1.5B-GGUF
1B • Updated • 340 -
IrieDinamik/LiquidAI-LFM2-1.2B-Tool-GGUF
Text Generation • 1B • Updated • 102 -
bartowski/Llama-3.2-3B-Instruct-GGUF
Text Generation • 3B • Updated • 179k • 254 -
bartowski/Llama-3.2-1B-Instruct-GGUF
Text Generation • 1B • Updated • 154k • 185
Curated CTranslate2 Whisper models verified for Vox Jot speech-to-text. Ranked: Fastest → Balanced → Best Quality → Experimental. MIT/Apache licensed,
-
Systran/faster-whisper-tiny
Automatic Speech Recognition • Updated • 2.34M • 36 -
Systran/faster-whisper-tiny.en
Automatic Speech Recognition • Updated • 351k • 10 -
Systran/faster-whisper-base
Automatic Speech Recognition • Updated • 2.03M • 53 -
Systran/faster-whisper-base.en
Automatic Speech Recognition • Updated • 1.02M • 9
Verified Story Studio creative-audio models and runtimes for Vox Jot.
Candidate on-device TTS models under evaluation for Vox Jot. Models here are not ranked or verified until full Vox Jot benchmark suites pass.
Public managed runtime for Vox Jot file ASR, diarization, Polyvoice routing, and emotion analysis.
Machine Learning Models
Curated speaker diarization and isolation models verified for Vox Jot file transcription.
-
pyannote/speaker-diarization-community-1
Automatic Speech Recognition • Updated • 5.1M • 3.72k -
pyannote/speaker-diarization-3.1
Automatic Speech Recognition • Updated • 6.92M • 4.85k -
BUT-FIT/diarizen-wavlm-large-s80-md-v2
Voice Activity Detection • Updated • 1.55k • 27 -
nvidia/diar_sortformer_4spk-v1
Automatic Speech Recognition • 0.1B • Updated • 101k • 163
Curated file-transcription ASR models verified for Vox Jot. File/audio engines, not live dictation hot path.
-
ibm-granite/granite-speech-4.1-2b
Automatic Speech Recognition • 2B • Updated • 180k • 168 -
CohereLabs/cohere-transcribe-03-2026
Automatic Speech Recognition • 2B • Updated • 93.7k • • 1.23k -
Systran/faster-whisper-large-v3
Automatic Speech Recognition • Updated • 1.47M • 705 -
mlx-community/nemotron-3.5-asr-streaming-0.6b
Automatic Speech Recognition • 0.6B • Updated • 1.48k • 18
Curated on-device OCR models verified for Vox Jot. Image-to-text and document scanning models optimized for local inference on-device.
Curated on-device LLM/GGUF models verified for Vox Jot. Small, fast instruct models optimized for local inference on-device.
-
IrieDinamik/LiquidAI-LFM2.5-Audio-1.5B-GGUF
1B • Updated • 340 -
IrieDinamik/LiquidAI-LFM2-1.2B-Tool-GGUF
Text Generation • 1B • Updated • 102 -
bartowski/Llama-3.2-3B-Instruct-GGUF
Text Generation • 3B • Updated • 179k • 254 -
bartowski/Llama-3.2-1B-Instruct-GGUF
Text Generation • 1B • Updated • 154k • 185
Curated on-device TTS models verified for Vox Jot speech synthesis. Ranked: Fastest → Balanced → Best Quality → Voice Cloning. MIT/Apache licensed.
Curated CTranslate2 Whisper models verified for Vox Jot speech-to-text. Ranked: Fastest → Balanced → Best Quality → Experimental. MIT/Apache licensed,
-
Systran/faster-whisper-tiny
Automatic Speech Recognition • Updated • 2.34M • 36 -
Systran/faster-whisper-tiny.en
Automatic Speech Recognition • Updated • 351k • 10 -
Systran/faster-whisper-base
Automatic Speech Recognition • Updated • 2.03M • 53 -
Systran/faster-whisper-base.en
Automatic Speech Recognition • Updated • 1.02M • 9