Together AI is now serving the two fastest speech-to-text models, according to Artificial Analysis. The NVIDIA Parakeet-TDT 0.6B v3 model can transcribe 20 hours of audio in less than 10 seconds. This performance is achieved through optimized systems including TensorRT profiling and conditional CUDA graphs. AI
IMPACT Accelerates real-time transcription capabilities, potentially impacting voice assistants and audio processing industries.
RANK_REASON A company is serving two of the fastest speech-to-text models, with one model achieving a notable speed benchmark. [lever_c_demoted from significant: ic=1 ai=0.7]
Read on X — Together (inference / OSS) →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →