Best open-source Text-to-Speech (TTS) models — SOTA neural voice synthesis, zero-shot cloning, multilingual & expressive speech generation.
Sinapsis AI
community
AI & ML interests
Agentic Platform Completely Open Source, Three Phases: - Agentic - Agents - Tools
Recent Activity
View all activity
Best Open Source models for Audio Classification (emotion, music genre, language ID, etc.)
-
MIT/ast-finetuned-audioset-10-10-0.4593
Audio Classification • 86.6M • Updated • 769k • 352 -
speechbrain/emotion-recognition-wav2vec2-IEMOCAP
Audio Classification • Updated • 489k • 184 -
laion/clap-htsat-fused
Audio Classification • 0.2B • Updated • 25.2M • 68 -
m-a-p/MERT-v1-330M
Audio Classification • Updated • 29.1k • 83
-
BAAI/bge-m3
Sentence Similarity • Updated • 14.6M • • 2.88k -
sentence-transformers/all-MiniLM-L6-v2
Sentence Similarity • 22.7M • Updated • 200M • • 4.65k -
google/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 1.18M • • 1.57k -
Qwen/Qwen3-Embedding-8B
Feature Extraction • 8B • Updated • 1.61M • • 631
Image to Image
Image To Video
Music & Sound Generation - Best Open Source models (MusicGen, Stable Audio, etc.)
Speech to Text (ASR) - Best Open Source models
-
openai/whisper-large-v3
Automatic Speech Recognition • Updated • 4.73M • • 5.54k -
openai/whisper-large-v3-turbo
Automatic Speech Recognition • Updated • 5M • • 2.89k -
nvidia/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • Updated • 161k • 1.45k -
facebook/seamless-m4t-v2-large
Automatic Speech Recognition • 2B • Updated • 90.9k • 967
Text to Image
Text to Video
The idea of this Collection is to gather those interesting models that are Open Source and I can use them in the webpage
-
moonshotai/Kimi-K2-Thinking
Text Generation • 1.1T • Updated • 55.5k • • 1.69k -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 8.44M • • 5.65k -
allenai/Olmo-3-32B-Think
Text Generation • 1.05M • Updated • 5.61k • 169 -
allenai/Olmo-3-7B-Instruct
Text Generation • 528k • Updated • 259k • • 124
-
Qwen/Qwen3-VL-235B-A22B-Thinking
Image-Text-to-Text • 236B • Updated • 357k • • 386 -
Qwen/Qwen3-235B-A22B-Instruct-2507
Text Generation • Updated • 178k • • 770 -
Qwen/Qwen-Image-Edit-2509
Image-to-Image • Updated • 232k • • 1.09k -
Qwen/Qwen3-VL-8B-Instruct
Image-Text-to-Text • 9B • Updated • 4.35M • • 850
Best open-source Text-to-Speech (TTS) models — SOTA neural voice synthesis, zero-shot cloning, multilingual & expressive speech generation.
Music & Sound Generation - Best Open Source models (MusicGen, Stable Audio, etc.)
Best Open Source models for Audio Classification (emotion, music genre, language ID, etc.)
-
MIT/ast-finetuned-audioset-10-10-0.4593
Audio Classification • 86.6M • Updated • 769k • 352 -
speechbrain/emotion-recognition-wav2vec2-IEMOCAP
Audio Classification • Updated • 489k • 184 -
laion/clap-htsat-fused
Audio Classification • 0.2B • Updated • 25.2M • 68 -
m-a-p/MERT-v1-330M
Audio Classification • Updated • 29.1k • 83
Speech to Text (ASR) - Best Open Source models
-
openai/whisper-large-v3
Automatic Speech Recognition • Updated • 4.73M • • 5.54k -
openai/whisper-large-v3-turbo
Automatic Speech Recognition • Updated • 5M • • 2.89k -
nvidia/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • Updated • 161k • 1.45k -
facebook/seamless-m4t-v2-large
Automatic Speech Recognition • 2B • Updated • 90.9k • 967
-
BAAI/bge-m3
Sentence Similarity • Updated • 14.6M • • 2.88k -
sentence-transformers/all-MiniLM-L6-v2
Sentence Similarity • 22.7M • Updated • 200M • • 4.65k -
google/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 1.18M • • 1.57k -
Qwen/Qwen3-Embedding-8B
Feature Extraction • 8B • Updated • 1.61M • • 631
Text to Image
Image to Image
Text to Video
Image To Video
The idea of this Collection is to gather those interesting models that are Open Source and I can use them in the webpage
-
moonshotai/Kimi-K2-Thinking
Text Generation • 1.1T • Updated • 55.5k • • 1.69k -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 8.44M • • 5.65k -
allenai/Olmo-3-32B-Think
Text Generation • 1.05M • Updated • 5.61k • 169 -
allenai/Olmo-3-7B-Instruct
Text Generation • 528k • Updated • 259k • • 124
-
Qwen/Qwen3-VL-235B-A22B-Thinking
Image-Text-to-Text • 236B • Updated • 357k • • 386 -
Qwen/Qwen3-235B-A22B-Instruct-2507
Text Generation • Updated • 178k • • 770 -
Qwen/Qwen-Image-Edit-2509
Image-to-Image • Updated • 232k • • 1.09k -
Qwen/Qwen3-VL-8B-Instruct
Image-Text-to-Text • 9B • Updated • 4.35M • • 850