Nari Labs Open-Sources Qwen3-TTS 1.7B: 50ms Latency at a Tenth the Cost
Nari Labs released an open-source TTS engine built on Qwen3-TTS 1.7B, claiming 50ms first-audio latency, 5x faster than Cartesia and 10x cheaper than ElevenLabs at $5 per million characters.
2026-09-11 ~ 2026-09-12 · 2 related posts
- Nari Labs launches 50ms TTS endpoint, 10x cheaper than ElevenLabs on Qwen3-TTS — iamaliveix · 2026-09-11
- Nari Labs open-sources Qwen3-TTS 1.7B: 50ms latency, 10x cheaper than ElevenLabs — alexcovo_eth · 2026-09-12