Model Releases: 310 curated resources

Curated material on model releases within frontier.

310 resources · page 6 of 10

• @runwayml (Runway)

  Creator not supplied; see original source.

  X account of Runway: releases of Gen video models and creative tools.

  Not applicable (entity) · unknown · unknown resource · en

• SAM 3D

  Creator not supplied; see original source.

  Top 3D AI listing for Meta SAM 3D, a 3D reconstruction model from the Segment Anything family.

  Not applicable (entity) · unknown · unknown resource · en

• Scribe v2

  Creator not supplied; see original source.

  Artificial Analysis speech-to-text page for ElevenLabs, covering Scribe v2: word error rate, speed and price compared with other models.

  Not applicable (entity) · unknown · unknown resource · en

• Seed3D v2.0

  Creator not supplied; see original source.

  Top 3D AI listing for ByteDance Seed3D v2.0 3D generation model with ratings.

  Not applicable (entity) · unknown · unknown resource · en

• Seedance 1.5 Pro

  Creator not supplied; see original source.

  ByteDance Seed page for Seedance 1.5 Pro video generation model.

  Not applicable (entity) · unknown · unknown resource · en

• Seedream 5.0 Pro

  Creator not supplied; see original source.

  ByteDance Seed page for Seedream 5.0 Pro image generation model.

  Not applicable (entity) · unknown · unknown resource · en

• SenseVoice

  Creator not supplied; see original source.

  QwenAudio SenseVoice GitHub repo: SenseVoiceSmall speech understanding model for Mandarin, Cantonese and other languages.

  Not applicable (entity) · unknown · unknown resource · zh

• Silero models

  Creator not supplied; see original source.

  Silero models GitHub repo: pretrained speech-to-text and text-to-speech models.

  Not applicable (entity) · unknown · unknown resource · en

• Silero VAD

  Creator not supplied; see original source.

  Silero VAD GitHub repo: pretrained voice activity detection model for streaming audio.

  Not applicable (entity) · unknown · unknown resource · en

• TripoSR

  Creator not supplied; see original source.

  VAST TripoSR GitHub repo: MIT-licensed fast 3D object reconstruction from a single image.

  Not applicable (entity) · unknown · unknown resource · en

• Sloyd

  Creator not supplied; see original source.

  Sloyd about page: AI creation platform for 3D, images, animation and video, grown from a game studio.

  Not applicable (entity) · unknown · unknown resource · en

• Sloyd AI v3

  Creator not supplied; see original source.

  Top 3D AI listing for Sloyd AI v3 3D generation tools and templates with ratings.

  Not applicable (entity) · unknown · unknown resource · en

• smallest-python-sdk

  Creator not supplied; see original source.

  Smallest AI Python SDK GitHub repo: official client for the Smallest AI speech API.

  Not applicable (entity) · unknown · unknown resource · en

• Smallest AI Pulse

  Creator not supplied; see original source.

  Artificial Analysis speech-to-text page for Smallest.ai, covering Smallest AI Pulse: word error rate, speed and price compared with other models.

  Not applicable (entity) · unknown · unknown resource · en

• Smallest AI Pulse Pro

  Creator not supplied; see original source.

  Artificial Analysis speech-to-text page for Smallest.ai, covering Smallest AI Pulse Pro: word error rate, speed and price compared with other models.

  Not applicable (entity) · unknown · unknown resource · en

• Solaria-3

  Creator not supplied; see original source.

  Artificial Analysis speech-to-text page for Gladia, covering Solaria-3: word error rate, speed and price compared with other models.

  Not applicable (entity) · unknown · unknown resource · en

• Sonic-3.6

  Creator not supplied; see original source.

  Cartesia post introducing Sonic-3.6, its multilingual real-time text-to-speech model covering 44 languages.

  Not applicable (entity) · unknown · unknown resource · mul

• Soniox v5 Async

  Creator not supplied; see original source.

  Artificial Analysis speech-to-text page for Soniox, covering Soniox v5 Async: word error rate, speed and price compared with other models.

  Not applicable (entity) · unknown · unknown resource · en

• Sony Music, Universal Music Group Sue Suno (Variety Australia)

  Creator not supplied; see original source.

  Variety report on Sony Music and UMG suing Suno over its label-backed model in September 2026.

  Not applicable (entity) · unknown · unknown resource · en

• Sora 2 Pro

  Creator not supplied; see original source.

  OpenAI API model page for Sora 2 Pro, noting the Sora 2 models and Videos API were shut down on 24 September 2026.

  Not applicable (entity) · unknown · unknown resource · en

• AudioLDM 2

  Creator not supplied; see original source.

  AudioLDM 2 GitHub repo: text-to-audio and music generation with a command-line interface.

  Not applicable (entity) · unknown · unknown resource · en

• Retrieval-based-Voice-Conversion-WebUI

  Creator not supplied; see original source.

  RVC WebUI GitHub repo: retrieval-based voice conversion with a web interface.

  Not applicable (entity) · unknown · unknown resource · en

• Spleeter (Deezer)

  Creator not supplied; see original source.

  Deezer Spleeter GitHub repo: audio source separation library with pretrained models for music stems.

  Not applicable (entity) · unknown · unknown resource · en

• Spotify Basic Pitch

  Creator not supplied; see original source.

  Spotify Basic Pitch GitHub repo: audio-to-MIDI converter with pitch bend detection.

  Not applicable (entity) · unknown · unknown resource · en

• Spotify Announces New AI Safeguards, Removes 75 Million 'Spammy' Tracks (Variety Australia)

  Creator not supplied; see original source.

  Variety report on Spotify's new AI safeguards and removal of 75 million spam tracks.

  Not applicable (entity) · unknown · unknown resource · en

• Stability AI research

  Creator not supplied; see original source.

  Stability AI research blog: reports on image, video, audio and 3D generative models.

  Not applicable (entity) · unknown · unknown resource · en

• Stable Diffusion

  Creator not supplied; see original source.

  CompVis stable-diffusion GitHub repo: original latent text-to-image diffusion model code.

  Not applicable (entity) · unknown · unknown resource · en

• Stable Fast 3D

  Creator not supplied; see original source.

  Stability AI Stable Fast 3D GitHub repo: fast single-image 3D mesh reconstruction with UV unwrapping.

  Not applicable (entity) · unknown · unknown resource · en

• Step 5 Preview

  Creator not supplied; see original source.

  StepFun documentation for the Step 5 Preview model: capabilities and API usage.

  Not applicable (entity) · unknown · unknown resource · en

• Step-Video-T2V (StepFun)

  Creator not supplied; see original source.

  StepFun Step-Video-T2V GitHub repo: 30B-parameter open text-to-video model.

  Not applicable (entity) · unknown · unknown resource · en

• StepAudio 3 ASR

  Creator not supplied; see original source.

  Artificial Analysis speech-to-text page for StepFun, covering StepAudio 3 ASR: word error rate, speed and price compared with other models.

  Not applicable (entity) · unknown · unknown resource · en

• Suno

  Creator not supplied; see original source.

  Suno: AI music generator creating songs from text prompts.

  Not applicable (entity) · unknown · unknown resource · en

Plain-text Markdown copy