Alibaba's Qwen3.5-Omni handles audio, video, images, and text in a single model pass - and generates speech in real time. The Plus variant hits SOTA on 215 benchmarks and edges out Gemini 3.1 Pro on audio tasks.
A deep look at Microsoft's three new in-house AI models - MAI-Transcribe-1, MAI-Voice-1, and MAI-Image-2 - and whether they live up to the hype.
Cohere releases its first audio model - a 2B-parameter open-source ASR system beating Whisper Large v3 by 27% on the HuggingFace Open ASR Leaderboard.
Mistral releases Voxtral, a pair of open-weights models covering speech recognition and text-to-speech that undercut OpenAI and ElevenLabs on price.
ElevenLabs Scribe v2 leads speech-to-text at 2.3% WER while ElevenLabs Flash v2.5 sets the pace for TTS with 75ms latency - but Google and Mistral are closing in fast.
IBM's new 1B-parameter speech model claims the top spot on the Open ASR Leaderboard while running on consumer hardware, beating Whisper Large V3 by 25% on word error rate.
Rankings of the best text-to-speech and speech-to-text AI models by naturalness, accuracy, latency, and pricing.
