{"version":1,"type":"story","url":"https://digestai.news/story/nari-unveils-qwen3tts-and-qwen3asr-with-low-latency-and-competitive-pricing","json":"https://digestai.news/story/nari-unveils-qwen3tts-and-qwen3asr-with-low-latency-and-competitive-pricing.json","markdown":"https://digestai.news/story/nari-unveils-qwen3tts-and-qwen3asr-with-low-latency-and-competitive-pricing.md","slug":"nari-unveils-qwen3tts-and-qwen3asr-with-low-latency-and-competitive-pricing","headline":"Nari unveils Qwen3‑TTS and Qwen3‑ASR with low latency and competitive pricing","summary":"Nari announced two new speech models, Qwen3‑TTS for text‑to‑speech and Qwen3‑ASR for automatic speech recognition. Both run on optimized API endpoints that promise enterprise‑grade latency and cost efficiency.\n\nIndependent measurements cited in the post show the TTS endpoint beating ElevenLabs on latency and price per million characters, while the ASR endpoint outperforms Deepgram on speed and hourly cost. The services are in a free public beta with early‑access pricing, and Nari says the stack uses custom kernels, batching, quantization and routing to hit the “Pareto frontier” on benchmark suites.\n\nNari also promotes dedicated or private deployment options and fine‑tuning capabilities, positioning the models for large‑scale production use. The announcement references the team behind Dia and Narvatar, suggesting a broader ecosystem for multimodal AI workloads.","keyPoints":["Qwen3‑TTS and Qwen3‑ASR launched with API endpoints optimized for low latency and cost.","Benchmarks show the TTS beats ElevenLabs and the ASR beats Deepgram in speed and price.","Nari offers free beta, early‑access pricing, and enterprise deployment options including dedicated infrastructure."],"whyItMatters":"Affordable, high‑performance speech models lower barriers for businesses to add voice capabilities, accelerating adoption of AI‑driven communication services.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["Nari","ElevenLabs","Deepgram","Dia","Narvatar"],"models":["Qwen3-TTS","Qwen3-ASR"],"people":[]},"firstPublishedAt":"2026-09-08T00:00:00Z","updatedAt":"2026-09-08T00:00:00Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"narilabs.com","title":"Show HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and cost","url":"https://narilabs.com/blog/nari-labs-leads-coval-voice-ai-benchmarks","publishedAt":"2026-09-08T00:00:00Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[{"site":"Hacker News","url":"https://news.ycombinator.com/item?id=49699267","points":44}],"thread":{"title":"AI Audio Arms Race Accelerates with Low‑Cost Real‑Time Voice","url":"https://digestai.news/thread/nari-unveils-qwen3tts-and-qwen3asr-with-low-latency-and-competitive-pricing","storyCount":5},"cite":{"text":"Digest AI, \"Nari unveils Qwen3‑TTS and Qwen3‑ASR with low latency and competitive pricing\", 8 September 2026, https://digestai.news/story/nari-unveils-qwen3tts-and-qwen3asr-with-low-latency-and-competitive-pricing","publisher":"Digest AI","title":"Nari unveils Qwen3‑TTS and Qwen3‑ASR with low latency and competitive pricing","datePublished":"2026-09-08T00:00:00Z","url":"https://digestai.news/story/nari-unveils-qwen3tts-and-qwen3asr-with-low-latency-and-competitive-pricing"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}