Topic · 6 stories
6 stories tagged speech-to-text on AI Tamer, newest first.
The Rust local inference server now transcribes and labels speakers on the CPU behind OpenAI-style routes. Its 0.9.0 and 0.9.1 downloads shipped without CUDA.
Nemotron 3.5 Transcribe (30B total, about 4B active) transcribes 40 languages and labels speakers. NVIDIA also opened the Granary v2 data pipeline.
Voxtral 3 pairs new Mistral transcription and speech models with a LiveKit-based voice agent SDK, on Mistral's API or self-deployed.
AssemblyAI announced Universal-3.6 Pro Realtime on 2026-09-29—streaming STT for voice agents, model id universal-3-6-pro. Drop-in versus 3.5 Pro (still available). $0.45/hr; billed by WebSocket session duration.
A practical guide to Whisper, Parakeet, Canary, Kokoro, and Piper, with a clear way to compare word error rate and check model licenses.
A practical map of speech recognition, language models, speech synthesis, direct speech-to-speech models, streaming, and the latency measurements that matter.
