Speech recognition

Source reports covering Speech recognition. Stories will appear when analysis and community reactions are ready.

8 reports · page 1 of 1

Connected topics are temporarily unavailable. You can still browse stories below.

Source reports

• Telus Uses AI to Alter Call-Agent Accents

  2026-05-06

  news

  3 min read

  Telus is utilizing AI technology from Tomato.ai to modify call-centre agents' accents in real time, aiming to reduce "accent-related friction." Labour groups have criticized this practice, calling it deceptive and advocating for mandatory disclosure.

  AI agentsTelecommunicationsEthical AI

• Microsoft VibeVoice: Open-Source Frontier Voice AI

  2026-04-28

  tool

  4 min read

  VibeVoice ASR is an open-source speech-to-text model that processes 60-minute long-form audio in a single pass, producing structured transcriptions with speaker identification, timestamps, and content. It is now integrated into the Hugging Face Transformers library for easy project implementation.

  Open sourceAI modelsDeveloper tools

• Cohere Transcribe: Speech Recognition

  2026-03-31

  tool

  5 min read

  Cohere has launched Transcribe, an open-source automatic speech recognition (ASR) model designed for high accuracy in practical conditions. The model supports various applications, including meeting transcription, speech analytics, and real-time customer support.

  Automatic speech recognitionAI modelsDeveloper tools

• Nvidia PersonaPlex 7B on Apple Silicon: Full-Duplex Speech-to-Speech in Swift

  2026-03-05

  tool

  5 min read

  NVIDIA PersonaPlex 7B enables full-duplex speech-to-speech communication on Apple Silicon, allowing simultaneous listening and speaking. The qwen3-asr-swift library processes audio in real-time, streaming generated audio chunks without a multi-step pipeline.

  NVIDIAApple siliconDeveloper tools

• Parakeet.cpp – Parakeet ASR inference in pure C++ with Metal GPU acceleration

  2026-02-27

  tool

  5 min read

  Frikallo/parakeet.cpp provides an ultra-fast and portable implementation of NVIDIA's Parakeet models for on-device speech recognition in C++. It achieves approximately 27ms encoder inference on Apple Silicon GPUs for 10 seconds of audio, making it 96 times faster than CPU processing, and utilizes the Axiom tensor library for automatic Metal GPU acceleration without heavy dependencies.

  NVIDIADeveloper tools

• Rust implementation of Mistral's Voxtral Mini 4B Realtime runs in your browser

  2026-02-10

  tool

  4 min read

  Voxtral Mini Realtime is a streaming speech recognition model implemented in pure Rust, utilizing the Burn ML framework. It operates natively in the browser via WASM and WebGPU, with a Q4 GGUF quantized version available for client-side execution.

  AI modelsRustWebgpu

• Pure C, CPU-only inference with Mistral Voxtral Realtime 4B speech to text model

  2026-02-10

  tool

  9 min read

  The GitHub repository provides a pure C implementation of the inference pipeline for Mistral AI's Voxtral Realtime 4B speech-to-text model, requiring only the C standard library. It features fast MPS inference, a chunked audio processing encoder to manage memory usage, and supports audio input from stdin or live microphone capture.

  Mistral AIAudio processingDeveloper tools

• Voxtral Transcribe 2

  2026-02-04

  5 min read

  Voxtral Transcribe 2 features two advanced speech-to-text models, Voxtral Mini Transcribe V2 for batch transcription and Voxtral Realtime for live applications, offering state-of-the-art transcription quality and ultra-low latency. Voxtral Realtime is available as open-weights under the Apache 2.0 license.

  Transcription technologyMistral AIReal time applications