In the news
The fastest, lowest-cost batch transcription with Qwen3-ASR
Baseten · Published · 3 min read
In 30 seconds
- What happened
- Baseten optimized Qwen3-ASR 1.7B for batch transcription, achieving 7x higher throughput and 1/10th cent per audio hour cost.
- Why it matters
- Matters for engineers building podcast, meeting notes, or call center transcription systems needing low-cost batch processing at scale.
- Watch out
- Optimizations are specific to RTX PRO 6000 hardware; real-time transcription workloads have different requirements and performance characteristics.
- transcription
- qwen
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.