←Back to NewsAI News/AudiomodelAudioInfraEdge0 Ships Audio8 ASR Infinite to Transcribe Speech for Hours StraightEdge0 open-sources a 4B streaming speech recognition model that runs 24/7 with a rolling KV cache, semantic turn detection, and configurable latency.SourceAlphaSignalPublishedSep 25, 2026, 12:45 AMAuthorAlphaSignal NewsroomRead1 min readEdge0 open-sources a 4B streaming speech recognition model that runs 24/7 with a rolling KV cache, semantic turn detection, and configurable latency.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsPika · newsPika Labs' Pika Speech Undercuts ElevenLabs by 9x With Studio-Quality AudioLiquid AI · newsLiquid AI's LFM2.5-VL DSpark Makes Vision AI 3.13x Faster on Apple SiliconDatabricks · newsDatabricks Buys Row Zero to Kill the Ungoverned Spreadsheet
