Conversational Voice · Streaming Text-to-Speech · Audio & Speech Models

Independent technical coverage of real-time voice AI infrastructure.

Latest research

Conversational Voice

View all →
  1. Voice Agent Handoff to Human Agents in Contact CentersContext-rich handoffs spare callers from repeating themselves to human agents.The Voice Layer EditorsNovember 16, 20269 min read
  2. Porcupine vs openWakeWord vs Custom Models for Embedded Wake WordsHardware limits and licensing, not benchmarks, decide which wake word engine fits.The Voice Layer EditorsNovember 11, 20268 min read
  3. Acoustic Echo Cancellation in Full-Duplex Voice AI SystemsHow voice AI stops hearing itself, from DSP filters to neural models.The Voice Layer EditorsNovember 11, 20268 min read
  4. Conversation State Management in Long-Running Voice AI SessionsMost voice agents ship, then lose the thread; bounded context fixes it.The Voice Layer EditorsNovember 11, 20268 min read

Streaming Text-to-Speech

View all →
  1. Sentence Boundary Detection for Streaming TTS Chunk SplittingHow to split streaming text for speech without breaking prosody.The Voice Layer EditorsNovember 11, 20268 min read
  2. Streaming TTS Voice Persona Consistency Across Long-Form OutputLong-form TTS systems lose voice consistency at scale, requiring new detection methods and fixes.The Voice Layer EditorsOctober 7, 20268 min read
  3. Streaming TTS Punctuation Handling for Natural Pause GenerationStreaming TTS systems use punctuation as real-time pacing commands to balance speed and naturalness.The Voice Layer EditorsSeptember 27, 202612 min read
  4. SSML Support Across Commercial TTS Streaming APIsDevelopers need to pick a TTS provider based on actual SSML support, not marketing claims.The Voice Layer EditorsSeptember 21, 202611 min read

Audio & Speech Models

View all →
  1. Phoneme-Level Timestamp Alignment in Speech Recognition APIsPhoneme-level timestamps require a separate alignment model, not just better transcription.The Voice Layer EditorsOctober 9, 202610 min read
  2. Noise Robustness Testing Methods for Production ASR DeploymentsProduction ASR systems fail in ways that standard benchmarks never measure.The Voice Layer EditorsOctober 8, 202610 min read
  3. Real-Time ASR Adaptation for Domain-Specific TerminologySpecialized speech systems need runtime vocabulary injection and fine-tuning to match domain audio.The Voice Layer EditorsOctober 6, 202610 min read
  4. Streaming ASR Word-Level Confidence Scores for Downstream NLP UseConfidence scores let downstream systems judge which ASR words to trust.The Voice Layer EditorsOctober 4, 20268 min read

Features

View all →
  1. Text Segmentation Heuristics That Reduce Streaming TTS Artifact BoundariesStreaming TTS seams come from early commitment, state resets, and capacity limits.The Voice Layer EditorsNovember 8, 20268 min read
  2. How Loudspeaker Feedback Reaches the Microphone and What Cancels ItUnderstanding how acoustic loops form and why placement matters most.The Voice Layer EditorsOctober 30, 20268 min read
  3. How Voice Agents Persist Session State Across Multi-Turn ConversationsVoice agents must store conversation memory outside the LLM to handle multi-turn dialogue.The Voice Layer EditorsOctober 19, 20269 min read
  4. Barge-in and turn-taking: how conversational voice systems handle interruptionWhy voice assistants struggle to know when you're interrupting them.The Voice Layer EditorsAugust 4, 20266 min read