Salesforce Releases SOV-Transcribe-1 Open-Weight Speech Model
Salesforce has released SOV-Transcribe-1, an open-weight speech model it says ranks first among open-weight non-streaming systems on Artificial Analysis.
Latest
Rime Launches Prism Speech-to-Speech Model With Inspectable Text
Rime's Prism speech-to-speech model writes out each reply before speaking it. Rime says it beats non-reasoning OpenAI and Google voice models on Ï„-Voice.
ElevenLabs and adELA Offer Free Voice Restoration for ALS in Spain
ElevenLabs and Spain's ALS association adELA will give people with ALS free access to a digital copy of their own voice, using new or old recordings.
28% of UK Adults Think Voice-Clone Scammers Targeted Them in a Year
28% of UK adults told Starling Bank they think a voice-clone scam targeted them. How the scam works, and why a family safe phrase beats a cloned voice.
Block Says Its Dessa Voice Model Learned to Talk Without Any Text
Block's Dessa is a full-duplex speech-to-speech model trained only on human conversation. It runs on a MacBook Pro; early access is for safety researchers.
IBM Says Granite Speech 5.0 2B Is Second-Best Open Model for English ASR
IBM has released Granite Speech 5.0 2B under Apache 2.0 for six-language transcription and translation, and refreshed two other speech models.
Mistral Launches Voxtral 3 Speech Models and a Voice Agent SDK
Mistral's Voxtral 3 adds speech-to-text in 50 languages, expressive TTS and a LiveKit-based voice agent SDK. Benchmark wins are Mistral's own claims.
ElevenLabs Launches Eleven Realtime Speech-to-Speech Models for Voice Agents
ElevenLabs launches Eleven Realtime v1 Mini and Max, speech-to-speech voice agent models with 90+ languages and an OpenAI-compatible API.
Grok Bot Update Adds Speed Claims, X Chat and New Connectors
Grok Bot (@bot) says computer tasks finish 3x sooner on average; adds X Chat, new connectors and marketplace submissions. Company claim; no benchmark.
OpenAI Opens Prompt-to-Voice to All API Customers, Adds Nine Voices
OpenAI changelog: prompt-to-voice GA for all API customers; nine new GPT-Live voices. GPT-Live only; max 100 voices/org. Docs only — no blog or X.
IBM Releases Granite Switch 4.1 With Decision Adapters and Fast Speech Recognition
IBM’s Granite Switch 4.1 packs Decision and Guardian aLoRAs plus Speech-5.0-Turbo-CTC in one endpoint. Leaderboard and speed figures are IBM’s claims.
Related stories
Latest from topics connected to Voice AI. See all with connected topics
Latest on TSN
Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.



