Nari Labs has achieved top rankings on the Coval voice AI benchmark for both its Qwen3-TTS and Qwen3-ASR models. The company's models excel in metrics such as time-to-first-audio (TTFA) and word error rate (WER) for text-to-speech, and time-to-final-segment (TTFS) and WER for speech-to-text. Nari Labs also highlights the cost-effectiveness of its offerings compared to competitors like AssemblyAI and ElevenLabs. AI
IMPACT Sets new performance and cost benchmarks for voice AI models, potentially influencing future development and adoption.
RANK_REASON The cluster reports on benchmark results for AI models, which falls under research.
Read on Mastodon — sigmoid.social →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →