GPT-Transcribe Makes Context the New ASR FeatureOriginalOpenAI's GPT-Transcribe launched July 29, 2026 with prompt, keyword, and language hints. Free-form context lifted accuracy from 38.5% to 44.6%.Speech-to-Text
Voice data residency decides where your agent runsOriginalVoice data residency decides where speech APIs process audio. Deepgram Australia went live June 17, 2026, shaping how teams pick STT and TTS providers.Voice AI
Three STT Strategies, One MarketOriginalBy June 2026 every major STT provider hit acceptable accuracy. The real competition moved to multilingual support, turn detection and platform integration.Voice AI
TIL: Flux natively knows when a caller finishes speakingOriginalDeepgram Flux turn detection replaces VAD and silence timeouts with model-native EndOfTurn events. A single WebSocket config parameter simplifies voice agent turn-taking.Voice AI
TIL: Deepgram keyterm prompting for accurate transcriptionOriginalImprove transcription accuracy for specialised terminology, product names, and technical jargon using Deepgram's keyterm prompting. One parameter that changes what the model hears.TIL
TIL: Testing speech-to-text with curlOriginalOne curl command transcribes audio through any REST-based STT API. No SDK, no imports, just your audio file and an API key.TIL
Why Speaker Diarization Is the Hardest Problem in Voice AIOriginalSpeaker diarization figures out who spoke when. It sounds simple. It is not. Here is why it breaks, and what it takes to get right.Voice AI
How streaming speech recognition worksOriginalStreaming speech-to-text sends audio chunks over WebSocket. Acoustic models, language models, and decoders explain the latency-accuracy tradeoff.Engineering
TIL: Processing STT Word Timestamps With awkOriginalawk parses word-level timestamps from STT output in one line. Extract, filter, and reformat without importing a CSV library.TIL