/ Audio and Speech

Mistral AI improves speech recognition: pause detection feature added

1 day ago

IBM Launches Granite Speech 5.0: Advanced Models for Enterprise Transcription and Translation

2 weeks ago

MistralAI introduces Voxtral 3: Advanced models for voice agents

2 weeks ago

Microsoft's MAI-Transcribe-2 Leads Transcription Accuracy Benchmark

2 weeks ago

OpenAI updated voices and accents for ChatGPT and Codex

3 weeks ago

TII Unveils Falcon-ASR: State-of-the-Art Speech Recognition for Emirati Arabic

1 month ago

Google AI introduces two advanced TTS models: Gemini 3.8 Flash

1 month ago

Gemini 3.8 Launches Highly Customizable, Enterprise-Grade Text-to-Speech

1 month ago

Alibaba Qwen-Audio-3.1: a complete audio stack with emotional response and multi-speaker recognition

1 month ago

Pika Details Its Video-to-Audio Soundtrack Model

2 months ago

Pika launches four lower-cost generative audio models

2 months ago

OpenAI Rebuilds Voice AI Around Full-Duplex Conversation

3 months ago

OpenAI Released Two Audio Transcription Models

3 months ago

GPT-Live Learns to Combine Dialogue with Multiple Tasks

3 months ago

Synthesia upgrades AI dubbing with better lip sync

3 months ago

Adobe Firefly adds text-based sound effects

3 months ago

OpenAI launches GPT-Live for live voice conversations in ChatGPT

3 months ago

OpenAI released GPT-Realtime-2.1-mini in the API

4 months ago

Meta Unveils SAM Audio: A Model for On-Demand Sound Separation

4 months ago