World Wire

Edge0 has released Audio8-TTS-Realistic , an open-weight text-to-speech model for zero-shot voice cloning. Audio8-TTS-Realistic is a 0.6B-parameter model that clones a voice from 1 reference clip and transcript. It supports 23 languages, 12 more than its predecessor. The weights and code ship under Apache 2.0 . For developers, the catch is competitive multilingual accuracy at a size that is cheap to fine-tune and serve. TL;DR Size: 601M main-model parameters (codec excluded); up to 2,048 packed text/audio positions of context. Runs on: a CUDA GPU is recommended; smoke-tested on NVIDIA H20 in BF16. The paper reports 1.1 to 1.2 GiB peak memory on an Apple M2 CPU (INT4 ONNX). No Realistic ONNX export is public yet. Performance: ahead of larger open models on CV3, behind 4B-class models on MiniMax. Best: 4.86% average CV3 error across 9 languages, versus 7.73% for Qwen3-TTS-1.7B. Worst: 48.57% WER on Thai (CV3) and 31.35% CER on Cantonese (MiniMax). What...

Block’s AI research lab has released Dessa , a full-duplex speech model trained only on human conversation. Block announced it on October 23, 2026 as a research preview. Dessa is a speech-to-speech model from Block that listens and talks at the same time. Block says it used no text and no pretrained models. That is a different design from the text-first stacks behind most voice agents today. TL;DR Runs on: A MacBook Pro M4 Max or better, locally, faster than real time. Performance: Demo-only so far. Live recordings show backchannels, mid-sentence laughs and natural interruptions. Best: Trained on 1 NVIDIA GB200 NVL72 rack (72 GPUs). Moshi used 1,016 H100 GPUs. Worst: 0 published benchmark scores. No weights, paper, API or price. What is Block’s Dessa? Dessa is a true speech-to-speech model: audio in, audio out. According to Block’s project page , everything it knows came from human speech. It is full-duplex, so it listens while i...

AssemblyAI has released AssemblyAI-TTS-1 , its first text-to-speech model, now generally available. The AssemblyAI-TTS-1 text-to-speech API targets voice agents running on live phone calls. In that setting, latency and pronunciation decide whether a caller stays on the line. Pricing is $15 per 1M characters , with no annual contract and no concurrency tier to buy. For developers already using AssemblyAI speech-to-text, it closes the voice loop with one vendor. TL;DR Size: It is a hosted API model. Runs on: AssemblyAI’s cloud only, in the US (us-east-1) or EU (eu-north-1) . No open weights or on-prem option. Any client with HTTP or WebSocket works. Performance: Ties ElevenLabs v4 on entity accuracy in AssemblyAI’s tests, at under 1/5 of its price. Best: 47 ms median time to first byte across 6 models in AssemblyAI’s API test (self-reported). Worst: 159 ms median streaming latency on Cekura’s independent benchmark , 8th of 19 timed mo...

NVIDIA has released Nemotron 3.5 Transcribe , an open-weights speech LLM built for transcription. One model handles 40 languages and recordings up to 1 hour . A text instruction picks the output style for each request. Options include verbatim, written form, speaker-attributed, contextual and translated output. For developers, it can replace separate ASR, diarization and alignment tools. TL;DR Size: 34B total and about 4.3B active parameters; 65,536-token context; audio up to 1 hour. Runs on: 1x H100 80 GB in BF16. FP8 (about 35 GB) and NVFP4 (about 21 GB) checkpoints exist; NVFP4 runs on an RTX 5090. GGUF files target NeMo-Speech.cpp. Performance: Best open-weights model on the English and multilingual Open ASR Leaderboards; top commercial APIs still lead. Best: 4.71% mean WER on the 9 public English Open ASR sets (next open model: 4.94%). Worst: 34.95% cpCER on AliMeeting Mandarin far-field meetings. Bottom line: Best thing: 1 open model covers tra...