utStability AI · Downloadable
stable-codec-speech-16k-base
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jan 14, 2025
- Parameters
- 953.4M
- 4-bit weights only
- ≈ 0.5 GB
- License
- other
WHAT’S NEW
New AI models.
Keep up without the noise.
The latest source listings from makers we track, covering language, images, video, audio, and 3D. Catalog checked Oct 28, 2026.
Sorted by the date a source repository was created, which may precede public release. This is a feed of new listings, not confirmed release announcements. Downloadable weights do not automatically mean an open-source license. Coverage and date meanings.
Audio listings
172 dated recordsStability AI · Downloadable
stable-codec-speech-16k
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jan 10, 2025
- Parameters
- 953.4M
- 4-bit weights only
- ≈ 0.5 GB
- License
- other
Fish Audio · Downloadable
fish-speech-1.5
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 24, 2024
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- cc-by-nc-sa-4.0
Fish Audio · Downloadable
fish-agent-v0.1-3b
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Oct 29, 2024
- Parameters
- 3B
- 4-bit weights only
- ≈ 1.5 GB
- License
- cc-by-nc-sa-4.0
OpenAI · Downloadable
whisper-large-v3-turbo
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Oct 1, 2024
- Parameters
- 808.9M
- 4-bit weights only
- ≈ 0.4 GB
- License
- mit
Fish Audio · Downloadable
fish-speech-1.4
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Sep 10, 2024
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- cc-by-nc-sa-4.0
Fish Audio · Downloadable
fish-speech-1.2-sft
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jul 18, 2024
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- cc-by-nc-sa-4.0
Fish Audio · Downloadable
fish-speech-1.2
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jul 2, 2024
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- cc-by-nc-sa-4.0
Stability AI · Downloadable
stable-audio-open-1.0
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- May 24, 2024
- Parameters
- 1.2B
- 4-bit weights only
- ≈ 0.6 GB
- License
- other
Fish Audio · Downloadable
fish-speech-1
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Apr 19, 2024
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- cc-by-nc-sa-4.0
Fish Audio · Downloadable
speech-lm-v1
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Dec 7, 2023
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- cc-by-nc-sa-4.0
pyannote · Downloadable
speaker-diarization-3.1
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 16, 2023
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- mit
OpenAI · Downloadable
whisper-large-v3
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 7, 2023
- Parameters
- 1.5B
- 4-bit weights only
- ≈ 0.8 GB
- License
- apache-2.0
pyannote · Downloadable
speaker-diarization-3.0
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Sep 22, 2023
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- mit
OpenAI · Downloadable
whisper-large-v2
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Dec 5, 2022
- Parameters
- 1.5B
- 4-bit weights only
- ≈ 0.8 GB
- License
- apache-2.0
OpenAI · Downloadable
whisper-medium.en
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Sep 26, 2022
- Parameters
- 763.9M
- 4-bit weights only
- ≈ 0.4 GB
- License
- apache-2.0
OpenAI · Downloadable
whisper-small.en
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Sep 26, 2022
- Parameters
- 241.7M
- 4-bit weights only
- ≈ 0.1 GB
- License
- apache-2.0
OpenAI · Downloadable
whisper-base.en
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Sep 26, 2022
- Parameters
- 72.6M
- 4-bit weights only
- ≈ 0 GB
- License
- apache-2.0
OpenAI · Downloadable
whisper-tiny.en
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Sep 26, 2022
- Parameters
- 37.8M
- 4-bit weights only
- ≈ 0 GB
- License
- apache-2.0
OpenAI · Downloadable
whisper-large
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Sep 26, 2022
- Parameters
- 1.5B
- 4-bit weights only
- ≈ 0.8 GB
- License
- apache-2.0
OpenAI · Downloadable
whisper-medium
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Sep 26, 2022
- Parameters
- 763.9M
- 4-bit weights only
- ≈ 0.4 GB
- License
- apache-2.0
OpenAI · Downloadable
whisper-small
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Sep 26, 2022
- Parameters
- 241.7M
- 4-bit weights only
- ≈ 0.1 GB
- License
- apache-2.0
OpenAI · Downloadable
whisper-base
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Sep 26, 2022
- Parameters
- 72.6M
- 4-bit weights only
- ≈ 0 GB
- License
- apache-2.0
OpenAI · Downloadable
whisper-tiny
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Sep 26, 2022
- Parameters
- 37.8M
- 4-bit weights only
- ≈ 0 GB
- License
- apache-2.0
What makes this feed useful?
Capability tags distinguish a model that reads images from one that creates them. Each listing links to its source and a permanent profile, so you can inspect its license and compare it with a model you already know.
Does this cover every new release?
No. The current feed tracks public Hugging Face metadata from selected makers. It can miss untracked makers, cloud-only releases, and records beyond a source’s retrieval limit. Announced models without a source listing are not included. Check Sources & methodology for the current coverage.
Listings update with the catalog automatically. A missing or delayed source can leave older information visible; each model profile shows when it was checked.