DEV Community

#stt

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
ElevenLabs Scribe v3 Live Cuts Semantic Errors 43% — Dual-Track WASAPI Still Sets the Latency Floor

ElevenLabs Scribe v3 Live Cuts Semantic Errors 43% — Dual-Track WASAPI Still Sets the Latency Floor

Comments
4 min read
Fish Audio Live 3 Claims 186 ms Full-Duplex Reactions — Dual-Track WASAPI Still Sets the Real Floor

Fish Audio Live 3 Claims 186 ms Full-Duplex Reactions — Dual-Track WASAPI Still Sets the Real Floor

Comments
4 min read
Claude Meetings Joins the Call — Your Overlay Still Lives on Dual-Track WASAPI Capture

Claude Meetings Joins the Call — Your Overlay Still Lives on Dual-Track WASAPI Capture

Comments
4 min read
ElevenLabs Scribe v3 Live Lands at 93 ms TTFS — Dual-Track WASAPI Capture Still Sets the Overlay Floor

ElevenLabs Scribe v3 Live Lands at 93 ms TTFS — Dual-Track WASAPI Capture Still Sets the Overlay Floor

Comments
4 min read
Speech Studio 0.5.0 Drops Local Multi-Engine TTS+STT on Windows — First-Sound Latency Still Sets the Overlay Floor

Speech Studio 0.5.0 Drops Local Multi-Engine TTS+STT on Windows — First-Sound Latency Still Sets the Overlay Floor

Comments
4 min read
NorSpeak: a free browser AI voice workbench (TTS, STT, live captions)

NorSpeak: a free browser AI voice workbench (TTS, STT, live captions)

Comments
2 min read
Recall.ai WASAPI Deep Dive Lands — Dual-Track Loopback Still Sets the Real Overlay Latency Floor

Recall.ai WASAPI Deep Dive Lands — Dual-Track Loopback Still Sets the Real Overlay Latency Floor

Comments
4 min read
Soniox STT v6 Adds Agent Text Input — Dual-Track WASAPI Capture Still Sets the Latency Floor

Soniox STT v6 Adds Agent Text Input — Dual-Track WASAPI Capture Still Sets the Latency Floor

Comments
4 min read
Qwen3 ASR 1.7B Hits 35 ms Time-to-Final on Coval — Windows Capture Still Owns the Real-Time Budget

Qwen3 ASR 1.7B Hits 35 ms Time-to-Final on Coval — Windows Capture Still Owns the Real-Time Budget

Comments
4 min read
Anthropic FlashProve: zkSNARK Model Provenance and the Unchanged Windows Capture Latency Problem

Anthropic FlashProve: zkSNARK Model Provenance and the Unchanged Windows Capture Latency Problem

Comments
6 min read
Soniox STT v6 Agent Text Injection: Residual Echo Filtering and Windows Capture Latency Budgets

Soniox STT v6 Agent Text Injection: Residual Echo Filtering and Windows Capture Latency Budgets

Comments
5 min read
Mistral Large 4 Open Weights Drop — Your Local Overlay Still Lives or Dies on the Capture Path

Mistral Large 4 Open Weights Drop — Your Local Overlay Still Lives or Dies on the Capture Path

Comments
4 min read
Building an Open-Source Alternative to ElevenLabs and Deepgram: Introducing RagLeap Voice

Building an Open-Source Alternative to ElevenLabs and Deepgram: Introducing RagLeap Voice

Comments
3 min read
Nemotron 3.5 Transcribe: One-GPU Promptable Offline STT for Multilingual Call Pipelines

Nemotron 3.5 Transcribe: One-GPU Promptable Offline STT for Multilingual Call Pipelines

Comments
4 min read
Azure LLM Speech 09-2026: 25 New Languages and 2 Faster Fast Transcription for Multilingual Call Pipelines

Azure LLM Speech 09-2026: 25 New Languages and 2 Faster Fast Transcription for Multilingual Call Pipelines

Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.