Models & Labs
Together AI Develops Fastest Speech-to-Text Stack
Together AI Bloghigh confidence
Why it matters
- →Together AI's stack significantly reduces transcription time, enhancing efficiency in audio processing.
- →The optimization of the entire data path sets a new standard for ASR performance.
- →This development is crucial for applications requiring rapid and accurate speech-to-text conversion.
.png)
Together AI has developed a highly efficient speech-to-text stack, utilizing NVIDIA's Parakeet-TDT and OpenAI's Whisper models. By optimizing the data path from CPU preprocessing to GPU execution, they have achieved the ability to transcribe 20 hours of audio in under 10 seconds. Key innovations include profile-aware TensorRT execution and GPU-side decoder control, which significantly enhance performance. This advancement is particularly impactful for applications that demand low latency and high throughput in audio transcription.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Build Real-Time Voice Agents on Together AI
Together AI Blog · March 12, 2026 · Related
- 2TurboQuant Introduces Extreme Compression for AI
Google Research Blog · March 24, 2026 · Background
- 3Deepgram STT and TTS Models on Together AI
Together AI Blog · April 2, 2026 · Related
- 4OpenAI Enhances WebRTC for Scalable Voice AI
OpenAI · May 4, 2026 · Related
- 5OpenAI Enhances API with New Voice Models
OpenAI · May 7, 2026 · Related
- 6OpenAI Adds Voice Intelligence to API
TechCrunch AI · May 7, 2026 · Background
- 7OpenAI Enhances Voice Agents with Real-Time Models
The Rundown AI · May 8, 2026 · Related
- 8OpenAI Unveils GPT-5.5 Instant for ChatGPT
The AI Advantage · May 8, 2026 · Background
What happened next
- 9NVIDIA Releases Nemotron 3.5 ASR for Multilingual Streaming
Sam Witteveen · June 7, 2026 · Related
- 10Benchmarking ASR on Code-Switched Speech
Hugging Face Blog · June 9, 2026 · Related
- 11Hugging Face and Cerebras Launch Real-Time Voice AI
Hugging Face Blog · July 1, 2026 · Related
- 12Google's Gemini 3.5 Transcribe Enhances AI Transcription
The Verge AI · August 26, 2026 · Background
- 13BreezeTTS2: Real-time local voice synthesis
Sam Witteveen · August 31, 2026 · Related
More in Models & Labs
Models & Labsmodels
llama.cpp b12029 adds CUDA 13 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally supporting NVIDIA's latest CUDA 13 stack alongside AMD's ROCm 10.0. The inclusion of native builds for Linux arm64 with Snapdragon chips, covering CPU, Adreno GPU, and Hexagon NPU, signals a serious push into mobile edge deployment. While Apple Silicon KleidiAI is disabled in this specific build, the broader hardware coverage means developers no longer need to compile from source for most modern accelerators. It’s less about new features and more about removing friction for anyone running local models on bleeding-edge or diverse hardware.
llama.cpp Releases
© The Verge AIModels & Labsother
Apple Intelligence arrives in China via iOS 27.3
Apple is finally unlocking its AI suite for Chinese users with the iOS 27.3 beta, marking a significant regulatory milestone after months of approval delays. The rollout relies on Alibaba’s Qwen model rather than OpenAI, integrating features like notification summaries and visual intelligence directly into the OS. By sidestepping the new Siri in favor of established text and image tools, Apple is prioritizing immediate utility over the full generative experience. This move effectively brings Apple’s AI capabilities to a massive new market, albeit with localized constraints that distinguish it from the global release.
The Verge AI
© Matt WolfeModels & Labsmodels
Google Releases Gemini 4 Carbon for Cost-Efficient Inference
Google launched Gemini 4 Carbon, a new model variant aimed at providing high performance at a lower cost for inference tasks.
Matt Wolfe