Nari
A voice technology product offering TTS and ASR solutions based on Qwen3. It is designed for high accuracy, low latency, and low cost, and supports the construction of a complete voice interaction loop covering both speech recognition and synthesis.
Timeline (last 90 days)
Nari has launched two speech models based on Qwen3: a text-to-speech (TTS) model and an automatic speech recognition (ASR) model
Nari claims its speech solution delivers outstanding performance in accuracy, latency, and cost
Nari offers TTS and ASR as a paired solution, enabling developers to build a complete voice interaction loop from ASR recognition to TTS synthesis
The Nari project title highlights three selling points: high accuracy, low latency, and low cost
The performance metrics claimed by Nari come primarily from the project team's own statements, and independent benchmark data and side-by-side comparisons with mainstream solutions such as Whisper are still lacking
The Show HN post received 8 points and 1 comment, and is at an early exposure stage
All Facts (5)
Nari claims its speech solution delivers outstanding performance in accuracy, latency, and cost
50%UnverifiedNari offers TTS and ASR as a paired solution, enabling developers to build a complete voice interaction loop from ASR recognition to TTS synthesis
50%UnverifiedThe Nari project title highlights three selling points: high accuracy, low latency, and low cost
50%UnverifiedThe performance metrics claimed by Nari come primarily from the project team's own statements, and independent benchmark data and side-by-side comparisons with mainstream solutions such as Whisper are still lacking
50%UnverifiedNari has launched two speech models based on Qwen3: a text-to-speech (TTS) model and an automatic speech recognition (ASR) model
60%