--- title: "How Together AI built the world’s fastest speech-to-text stack" url: https://daily.dev/posts/how-together-ai-built-the-world-s-fastest-speech-to-text-stack-zje9zzhdu source_url: https://www.together.ai/blog/how-together-ai-built-the-worlds-fastest-speech-to-text-stack type: article source: "Together AI" published: 2026-05-31T07:40:50.762Z updated: 2026-05-31T08:18:43.280Z tags: ["python", "cuda", "speech-recognition"] reading_time: 9 upvotes: 0 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # How Together AI built the world’s fastest speech-to-text stack **[Together AI](https://daily.dev/sources/togetherai)** · 9 min read · 0 upvotes · 0 comments ## Summary Together AI details the systems engineering behind their fastest-ranked speech-to-text stack on Artificial Analysis, serving NVIDIA Parakeet-TDT 0.6B v3 and OpenAI Whisper Large v3. Key optimizations include: multi-profile TensorRT engines tuned for real audio input shapes to avoid padding overhead; conditional CUDA graph nodes that move the decoder's branch logic onto the GPU, eliminating CPU round-trips and achieving 2-3x decoder speedup; collapsing preprocessing microservices to reduce kernel copies, using Unix domain sockets and shared memory for zero-copy audio transfer; switching from thread-per-connection to epoll-based evented I/O for streaming to reduce GIL contention and tail latency; and using gc.freeze() after startup preallocation to prevent Python's garbage collector from walking large long-lived object graphs, eliminating ~200ms p95 latency spikes. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#python](https://daily.dev/tags/python), [#cuda](https://daily.dev/tags/cuda), [#speech-recognition](https://daily.dev/tags/speech-recognition) [View this post on daily.dev](https://daily.dev/posts/how-together-ai-built-the-world-s-fastest-speech-to-text-stack-zje9zzhdu)