Blog
Analysis, model profiles and deep dives on speech-to-text.
Analysis, model profiles and deep dives on speech-to-text.
Published July 3, 2026
What Cartesia's Ink-Whisper got right on latency, where its accuracy fell behind by 2026, and why it mattered more as a stepping stone than a benchmark.
Published July 3, 2026
Reference profile of Ink-Whisper, Cartesia's Whisper-derived streaming speech-to-text model for real-time voice agents, launched June 10, 2025.
Published July 3, 2026
Reference spec sheet for OpenAI's Whisper model as offered on Microsoft Azure: delivery paths, limits, languages, pricing, benchmarks, and release history.
Published July 3, 2026
Reference profile of OpenAI Whisper large-v3: architecture, training data, release history, deployment options, pricing, limitations, and sources.
ElevenLabs' Scribe v2 Realtime claims sub-150 ms latency, 93.5% accuracy in 30 languages, and $0.39/hr pricing. What the public record actually supports.
Published July 3, 2026
Reference profile of Scribe v2 Realtime, ElevenLabs' streaming speech-to-text model released November 11, 2025: specs, benchmarks, pricing, limits.
Published July 3, 2026
AssemblyAI's Universal-3 Pro reviewed: promptable transcription, WER benchmarks, pricing, compliance caveats, and what the public record still hides.
Published July 3, 2026
How OpenAI's Whisper large-v3 went from MIT-licensed research artifact to the baseline layer of a managed transcription stack, and what got left unresolved.
Published July 3, 2026
How Microsoft packages OpenAI's Whisper across Azure OpenAI and Azure Speech: limits, pricing signals, benchmarks, security, and where it fits in 2026.
Page 5 of 5
