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...
#text-to-speech
Array
(
[post_type] => post
[posts_per_page] => 12
[paged] => 1
[post_status] => publish
[tax_query] => Array
(
[relation] => AND
[0] => Array
(
[taxonomy] => post_tag
[field] => term_id
[terms] => 21541
[operator] => IN
)
)
)
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.
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...
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...
Voice AI Company WellSaid Closes Venture Debt Round to Fund Enterprise SalesÂ
AI text-to-speech company WellSaid takes on venture debt to fund enterprise sales push in crowded...
What Text-to-Speech Evaluation Misses in Real-World Deployment
Researchers argue that text-to-speech evaluation under-tests what matters in real-world deployment — and propose a...
Alibaba Expands Speech Stack with New Open-Source Models
Alibaba’s Qwen team releases a new set of open-source speech models under the Qwen3 family,...
Researchers Begin Benchmarking Cross-Lingual Voice Cloning
A new cross-lingual voice cloning track at IWSLT 2026 highlights changing priorities in multilingual speech...
NVIDIA Doubles Down on Open Speech AI
NVIDIA doubles down on open speech AI with ultra-low-latency automatic speech recognition and multilingual text-to-speech...
Resemble AI Open-Sources Chatterbox Turbo
Resemble AI releases an open-source text-to-speech model designed for real-time, expressive voice generation and positioned...
Adobe Firefly Launches New Feature for Multilingual AI Voiceovers
At its annual Adobe MAX 2025 conference, Adobe announced a new feature for its Firefly...