New Speech-to-Text Models, Updates, and Benchmarks to Watch
Recent speech-to-text updates span model launches, product updates, and new benchmarks.
Speech & voice
Dubbing and subtitling news from streaming, gaming etc.
AI Voice Clones More Intelligible Than Humans in Noise, Study Finds
A new study finds AI voice clones can be easier to understand than human speech...
Zoom’s In-House AI Live Speech Translation Goes Live — With Limits
Zoom rolls out its in-house AI live speech translation in beta — but with limited...
AI Voice Startup Palabra Launches TTS Engine, Names New CTO
AI voice developer, Palabra, appoints Andrey Feldman as new CTO to advance the firm’s AI...
As Voice AI Scales, New Tools Help Track Breakdowns Across the Voice Stack
As voice agents scale, debugging and monitoring become critical. New tools highlight a growing focus...
How Voice AI Companies Turn to M&A When Partnerships No Longer Compound
Acquisitions can help voice AI companies unlock scale and coherence, allowing for tighter bundling, higher...
Gladia Pushes Transparency in Speech AI Benchmarking
With new benchmarks and tools, Gladia is pushing transparency in speech AI evaluation — while...
Accent Leakage and Flat Voices: How Amazon Is Making AI Voices More ExpressiveÂ
Amazon notes that accent inconsistency, flat speech, and reliability issues still limit AI voice and...
How Voice AI Companies Eliminate Workflow Friction with Integrations
Voice AI companies that treat integrations as core infrastructure align naturally with how modern enterprises...
Microsoft Rolls Out New Speech Models in Push Toward First-Party AI Stack
Microsoft unveils in-house transcription and speech synthesis models, expanding its first-party speech AI stack.
How Voice AI Companies Build on Hyperscalers Without Competing
Voice AI companies can gain trust, procurement access, and scale by building on hyperscaler compute,...
Mistral Completes Voxtral Speech Stack With Launch of Text-to-Speech Model
Mistral launches Voxtral TTS, adding speech generation to its Voxtral model family and enabling end-to-end...
AssemblyAI Pushes into Healthcare with Medical Mode for Clinical Transcription
AssemblyAI launches Medical Mode, a domain-specific speech-to-text add-on designed to improve recognition of medical terminology...
Hume AI’s Early 2026 Moves Highlight Growing Focus on Voice AI Infrastructure
A busy start to 2026 for voice AI company Hume AI, with leadership changes, new...