Stars Radar
Support
LiveUpdated 2026-09-19 16:19 UTC

Models & inference

Models & inference scores 62/100 on the Stars Radar money board (#4), with 12 posts and 242.2k views on X over the last 365 days.

2 new tools appeared in this market over the last 7 days, and 2 posts were published about it in the last 72 hours. Jev also rates the room for a newcomer here 2/4.

Top Models & inference tools

colibri

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

Models & inference · 1 post · first seen 2 days ago · justvugg

models.dev

An open-source database of AI models.

Models & inference · 1 post · first seen 1 days ago · anomalyco

VoxCPM

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

Models & inference · 1 post · first seen 15 days ago · openbmb

parakeet

OpenAI Whisper-compatible ASR server using NVIDIA Parakeet TDT 0.6B (ONNX). Super fast CPU/GPU transcriptions

Models & inference · 1 post · first seen 23 days ago · achetronic

OmniVoice

High-Quality Voice Cloning TTS for 600+ Languages

Models & inference · 1 post · first seen 39 days ago · k2-fsa

whisper.cpp

Port of OpenAI's Whisper model in C/C++

Models & inference · 1 post · first seen 106 days ago · ggml-org

moshi

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Models & inference · 1 post · first seen 100 days ago · kyutai-labs

ultravox

A fast multimodal LLM for real-time voice

Models & inference · 1 post · first seen 100 days ago · fixie-ai

magnitude

Open source inference engine optimized for consumer hardware. Profiles your machine, recommends the best models for it, then downloads, tunes, and runs them.…

Models & inference · 1 post · first seen 41 days ago · magnitudedev

VibeVoice

Open-Source Frontier Voice AI

Models & inference · 1 post · first seen 43 days ago · microsoft

Qwen3-Omni

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as…

Models & inference · 1 post · first seen 100 days ago · qwenlm

csm

A Conversational Speech Generation Model

Models & inference · 1 post · first seen 100 days ago · sesameailabs

FAQ

Is there money in models & inference?

Jev rates buyer spend 0/4, search demand 0/4, sponsor budgets 0/4 and growth 0/4. Overall market score: 62/100 (#4 of 10).

What are the newest models & inference tools?

colibri, models.dev, VoxCPM, parakeet, OmniVoice. Updated 2026-09-19 16:19 UTC.

How is this ranked?

35% money (Jev judgment), 25% traction on X, 20% momentum over 72 hours, 10% new tools, 10% room for newcomers. See methodology.

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 209 posts from 1 X accounts over the last 365 days, 209 tools, 10 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 16:19 UTC. Full method.