{"type":"post","id":"the-fastest-lowest-cost-batch-transcription-with-qwen3-d86f64","slug":"the-fastest-lowest-cost-batch-transcription-with-qwen3-d86f64","title":"The fastest, lowest-cost batch transcription with Qwen3-ASR","description":"Baseten says it has optimized Qwen3-ASR 1.7B for high-concurrency batch transcription, reporting up to seven times the throughput of upstream vLLM on one RTX PRO 6000.","retrieval_nugget":"Baseten says it has optimized Qwen3-ASR 1.7B for high-concurrency batch transcription, reporting up to seven times the throughput of upstream vLLM on one RTX PRO 6000. For AI teams processing recorded calls, meetings, or media archives, the important change is an implementation path that makes cost per processed audio hour a system-design question.","published_at":"2026-10-28","updated_at":"2026-10-28","record_date":"2026-10-28","date_kind":"published_at","topics":["agent-economics","model-routing"],"entities":["Baseten","Qwen3-ASR 1.7B","vLLM","RTX PRO 6000","torchcodec","FlashInfer","Nemotron 3 Diarization","Qwen"],"related_patterns":["agent-economics-moves-to-completed-work"],"novelty_label":"new_fact","what_changed":"Baseten reports Qwen3-ASR batch-transcription optimizations delivering 7× higher throughput, 6.9× lower latency and roughly $0.001 per audio hour, with no meaningful quality loss.","prior_refs":["memory:8f7aca34-1673-8083-ac40-da4a4291ca09"],"source_url":"https://www.baseten.co/blog/fastest-lowest-cost-qwen3-asr-batch-transcription","source_urls":["https://www.baseten.co/blog/fastest-lowest-cost-qwen3-asr-batch-transcription"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:the-fastest-lowest-cost-batch-transcription-with-qwen3-d86f64","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/the-fastest-lowest-cost-batch-transcription-with-qwen3-d86f64/","markdown":"https://newruntime.com/posts/the-fastest-lowest-cost-batch-transcription-with-qwen3-d86f64.md","json":"https://newruntime.com/posts/the-fastest-lowest-cost-batch-transcription-with-qwen3-d86f64.json"},"next_reads":[{"type":"topic","path":"/topics/agent-economics/","url":"https://newruntime.com/topics/agent-economics/","title":"Agent Economics","reason":"Explore the agent-economics topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agent-economics.md","json_url":"https://newruntime.com/topics/agent-economics.json"},{"type":"topic","path":"/topics/model-routing/","url":"https://newruntime.com/topics/model-routing/","title":"Model Routing","reason":"Explore the model-routing topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/model-routing.md","json_url":"https://newruntime.com/topics/model-routing.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}