| 3 tips for better voice agent evalsShort | Sep 29, 2026 | 2:56 | 925 |
| Converse Code - A Voice controlled Coding AgentShort | Aug 18, 2026 | 1:23 | 1.3K |
| Which Voice AI Models Respond FastestShort | Aug 12, 2026 | 2:47 | 642 |
| Does Voice AI Hear You or Read You?Short | Aug 11, 2026 | 0:47 | 2.3K |
| Founding Team Nominations | Jul 23, 2026 | 4:17 | 730 |
| Trelis Tara - A Frontier Hindi Transcription Model [Open Weights]Short | Jul 22, 2026 | 0:35 | 297 |
| Trelis Tara - Frontier Hindi Transcription [Open Weights] | Jul 22, 2026 | 4:15 | 488 |
| Trelis Tiron - Open Weights State-of-the-Art Multi-speaker Meeting Transcription and AttributionShort | Jul 21, 2026 | 0:35 | 364 |
| Trelis Tiron - State-of-the-Art Multi-speaker Meeting Transcription and Attribution (Open Weights!) | Jul 21, 2026 | 11:13 | 819 |
| Whisper Hinglish - SotA Open Weights Model with Code-switching Capabilities | Jun 18, 2026 | 3:45 | 914 |
| Audio Dataset Cleaning: All that glisters is not Gold | Jun 2, 2026 | 6:38 | 719 |
| State of the Art Meeting TranscriptionShort | May 28, 2026 | 0:27 | 689 |
| State of the Art Meeting Transcription with Overlapping Speakers and Speaker-Identification | May 28, 2026 | 6:53 | 692 |
| Transcribe 1,600+ Languages with OmniASR | May 9, 2026 | 8:54 | 1.4K |
| Overlapping Speech Transcription, SolvedShort | Apr 20, 2026 | 0:36 | 1.5K |
| Chorus v1: Overlapping Speech Transcription, Solved | Apr 20, 2026 | 4:06 | 1.2K |
| Trelis Voice Loop — A Local Agent in ~500 Lines of CodeShort | Apr 13, 2026 | 1:16 | 1.6K |
| Voice Loop — A Local Voice Agent in ~500 Lines of Python | Apr 13, 2026 | 14:31 | 3.6K |
| Best Medical Transcription (ASR) Models | Apr 9, 2026 | 20:55 | 1.2K |
| Top Text-to-Speech (TTS) Models in 2026 | Mar 31, 2026 | 28:16 | 11.5K |
| Some Modern Voice AI Theory | Mar 30, 2026 | 9:44 | 971 |
| How to YOLO with Claude Code? | Mar 18, 2026 | 28:28 | 2.3K |
| Top Transcription / ASR Models in 2026 | Mar 11, 2026 | 14:42 | 4.8K |
| Trelis Voice Router - “OpenRouter for Voice” | Mar 6, 2026 | 3:58 | 815 |
| Train Voxtral Transcription (ASR) Models | Feb 27, 2026 | 17:20 | 2.4K |
| Transcription Models Zero to Hero - Data Prep, Train + Serve | Jan 15, 2026 | 19:17 | 1.7K |
| Align Audio and Text for Speech Recognition Model Training | Jan 14, 2026 | 26:57 | 3.5K |
| Is Recursion the Frontier for LLM ReasoningShort | Dec 19, 2025 | 0:55 | 2.2K |
| Training Recursive Models - A Frontier in Adaptive Compute | Dec 18, 2025 | 38:03 | 6.1K |
| Jean-François Puget et les Navy Seals de Nvidia | Dec 10, 2025 | 8:51 | 324 |
| An Interview with NVARC - 2025 ARC Prize Competition Winner | Dec 9, 2025 | 1:07:16 | 580 |
| British and American English Whisper TranscriptionShort | Dec 9, 2025 | 0:48 | 1.6K |
| Transcribe British and American English Variants | Dec 8, 2025 | 17:43 | 522 |
| Testing an LLM trained with just $100Short | Dec 4, 2025 | 1:06 | 1.6K |
| Train an LLM with just $100Short | Dec 3, 2025 | 0:25 | 3.2K |
| Train an LLM from Scratch with Karpathy's Nanochat | Dec 2, 2025 | 29:05 | 9.1K |
| Whisper Data Preparation and Unsloth Fine tuning TutorialShort | Nov 26, 2025 | 0:41 | 375 |
| Whisper Data Preparation and Fine tuning with Unsloth | Nov 25, 2025 | 41:29 | 5.8K |
| How to Create Synthetic Voices with KokoroShort | Nov 24, 2025 | 1:49 | 2.5K |
| Text to Speech Conversion with KokoroShort | Nov 22, 2025 | 0:48 | 2.7K |
| Run a Kokoro Text to Speech Locally or as a High-throughput Server | Nov 21, 2025 | 12:53 | 8.6K |
| Solving ARC Tasks by Writing Python Programs | Nov 7, 2025 | 1:07:30 | 389 |
| Post-training TRM & A Retrospective on ARC Prize 2025 | Nov 6, 2025 | 1:38:09 | 394 |
| Understanding TRM and HRM | Oct 10, 2025 | 1:00:49 | 2K |
| All about LoRA | Oct 4, 2025 | 49:23 | 824 |
| How to avoid going OOM? | Sep 27, 2025 | 46:02 | 390 |
| ARC AGI Chat | Unsloth OSS Update | Kyutai STT Update | Sep 20, 2025 | 53:02 | 459 |
| Faster fine tuning with Unsloth and Multi GPUShort | Sep 3, 2025 | 0:38 | 1.8K |
| Multi GPU Training with Unsloth | Sep 3, 2025 | 54:22 | 5.6K |
| Trelis Research LIVE: vLLM v0 vs v1. Data vs Tensor Parallel Inference & Fine-tuning. | Aug 29, 2025 | 49:19 | 738 |