New models and versions, open weights, and changes in capability and pricing, with their evaluations.
We’re proud to share that Meta Omnilingual Automatic Speech Recognition (ASR) has been named one of @TIME’s Best Inventions of 2026! Meta Omnilingual ASR is a suite of models providing ASR capabilities for over 1,600 languages, including 500 low-coverage languages never before https://t.co/pQjBPvE5XG
IBM released Granite-Switch-4.1-8B and -30B, combining chat, a general-purpose Decision aLoRA, a specialized Guardian aLoRA, and Granite-Speech-5.0-Turbo-CTC transcription through one hosted endpoint. IBM says the combined model uses approximately the same GPU VRAM as its base model, with adapters reusing the base model’s KV cache. Users can also compose custom Switch models from Granite Libraries adapters; an Adapter SDK for training adapters in Mellea is planned.
Why it matters: Shared KV caches and modular adapters offer a concrete approach to combining general and specialized decisions with transcription while keeping GPU memory use close to the base model.
Artificial Analysis evaluated SpaceXAI’s Grok Voice 3.0 using the Rex voice through the SpaceXAI Realtime API, reporting a #1 Speech to Speech Index score of 86.9, up from Grok Voice 2.0 at 81.3. It ranked #3 in arena preference and #1 in task success rate at 94.8%. Average time to first audio on Big Bench Audio was 0.81 seconds versus 0.70s for Grok Voice 2.0, while input audio pricing remained $4.80 per hour.
Artificial Analysis reports that Fish Audio’s Drama 3 Preview ranks #1 among open-weights models on all three of its Text to Speech leaderboards and leads all models in Pronunciation Robustness. It scores 93.2% on pronunciation robustness, ahead of Eleven v4 at 91.7% and Eleven v4 Turbo at 90.1%, while ranking #10 in Provider Voice and #14 in Controlled Voice. Its weights are available on Hugging Face under the Fish Audio Community License, and Fish Audio API pricing is $15/1M characters.
Why it matters: The comparison separates pronunciation robustness from voice preference rankings, showing how Drama 3 Preview’s lead on one measure differs from its placement on others.
HeyGen Voice ranks #1 on Artificial Analysis’s Controlled Voice TTS Arena leaderboard, which evaluates models using the same 8 cloned voices across US and UK English. Its Elo is 1,201 across 1,468 arena appearances, ahead of Qwen-Audio-3.1-TTS-Plus at 1,182 and Eleven v4 Turbo at 1,166. HeyGen Voice scores 83.1% on Pronunciation Robustness, ranking #10 of 29 models; it costs $30/1M characters and generates 40 characters per second of generation time.
Abu Dhabi's Technology Innovation Institute (TII) released Falcon-ASR, a 1.6B-parameter speech recognition model focused on Arabic and Emirati dialects, with support for English, French, Spanish, and Portuguese as well. Its average WER across six Arabic test sets is 20.92%, 2.25 percentage points below the best public result of 23.17% in the leaderboard snapshot used. In an internal Emirati dialect evaluation, it achieved a 22.73% WER and 10.19% CER, outperforming Qwen3-Omni.
Microsoft AI released MAI-Transcribe-2-Streaming, a real-time transcription model supporting 60 languages. Its first partial results arrive in just over 100 milliseconds. Microsoft says it ranks first for accuracy on Artificial Analysis; audio costs $0.54 per hour through the end of the year.
Tavus launched Griffin, which the company calls the first Human Interaction Model (HIM). In live video calls, it can receive and generate speech, facial expressions, tone of voice, gestures, and pauses at the same time.
Microsoft AI is launching MAI-Transcribe-2-Streaming, which Mustafa Suleyman calls the world's most accurate real-time transcription model. He claims it is 55% faster and 60% cheaper than ElevenLabs and invites developers to build agents on Microsoft's platform. In the quoted post, Artificial Analysis reports #1 rankings for final and first partial transcript accuracy on AA-WER Streaming, with final transcript WER of 2.5% at 0.13s after speech ends and streaming pricing of $0.54 per hour of audio.
Why it matters: The quoted benchmark comparison pairs transcription accuracy with latency and pricing, giving readers concrete tradeoffs to consider when choosing a streaming speech model for agents.
On September 28, Alibaba's Qwen-Audio-3.1-TTS speech model ranked first globally on the Controlled Voice Arena leaderboard by Artificial Analysis with an Elo rating of 1,177.
ElevenLabs released voice model Eleven v4, which better follows emotion, pauses, and sound-effect tags in scripts and keeps voices consistent in long productions. The new architecture also powers Turbo, a variant for real-time voice agents. In company tests, it begins speaking in about 150 milliseconds, compared with 262 milliseconds for Cartesia Sonic 3.6 and 814 milliseconds for OpenAI GPT-4o mini TTS.
Google DeepMind has released Gemini 3.8 Live with Live Avatar, combining real-time video generation and voice to give Gemini's conversational model a near-real-time visual avatar, with accurate lip-sync, natural expressions, and smooth turn-taking.
Why it matters: Gemini 3.8 Live adds real-time video avatars, giving readers a view of how multimodal conversation is being applied in enterprise settings and where the feature is available.
Google has released the Gemini 3.8 Flash and Flash-Lite text-to-speech models, describing them as new state-of-the-art voice models. They offer a new voice-design experience, more than 2,000 production-ready voices, voice cloning, and support for 100 languages; voice mixing is coming soon. Google says they rank first on Hume AI's voice benchmark.
Why it matters: Google's Gemini 3.8 Flash and Flash-Lite TTS release lists more than 2,000 voices, support for 100 languages, voice cloning, and other capabilities.
Google DeepMind has released two text-to-speech models. Gemini 3.8 Flash TTS can design custom voices with different accents and characteristics; Gemini 3.8 Flash-Lite TTS is aimed at efficiency and scale, with a choice of custom styles or an official library of production-ready voices. The company says they can be used to create and deploy custom audio.
Google DeepMind has released two speech-generation models: Gemini 3.8 Flash TTS for character design and fine-grained creative control, and Gemini 3.8 Flash-Lite TTS for high-volume voiceovers and voice agents.
Why it matters: The article outlines the models' voice cloning, line-by-line direction, and benchmark results, helping readers assess their suitability for dubbing and podcast production.
Alibaba has released Qwen-Audio-3.1 with upgrades to ASR, TTS, and Realtime, plus two new models, TTS-Next and ASR-Next. Five models now cover audio understanding, generation, interaction, and creation.
Why it matters: The article lists the capabilities of all five audio models and their price reductions, helping readers assess voice-stack choices and cost changes.
Google has released Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, new state-of-the-art real-time audio models positioned for leading price and performance. Gemini 3.8 Live supports 97 languages with seamless switching, as well as asynchronous tool calls and other features.
Why it matters: Google's new real-time audio models offer language coverage and asynchronous tool calls, helping readers assess the practical limits of live voice interaction.
Google DeepMind has released two real-time voice-conversation models: Gemini 3.8 Live for scale and cost efficiency, and Gemini 3.8 Live Extended Thinking for complex tasks and multi-step reasoning.
Why it matters: The two live voice models support parallel reasoning and tool calls and report results on several speech benchmarks, offering a way to assess the limits of voice agents.
Google DeepMind has released Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, calling them its best conversational AI yet. The company says the models can converse and think while handling tasks in the background without interrupting the user's workflow.
Why it matters: The new conversational models give readers an update on Google DeepMind's positioning for real-time dialogue and background task handling.
Google DeepMind has released Gemini 3.5 Transcribe, which it calls its most accurate speech-to-text model yet. It converts raw audio directly into accurate, formatted text.
Why it matters: The official post reports WER for streaming and non-streaming APIs and compares the model with the previous-generation Chirp 3, helping readers assess speech transcription in practical workflows.
NVIDIA has released Magpie TTS Multilingual, a 364M-parameter open-weights speech-synthesis model supporting 12 languages. The latest release adds Modern Standard Arabic, Korean, and Brazilian Portuguese, and improves quality in several existing languages through updated training data.
Why it matters: The article reports the 364M open TTS model's language expansion and measured TTFA on different GPUs, helping readers estimate latency budgets for self-hosted voice pipelines.
Google DeepMind has released Lyria 3.5, its next-generation music-generation model, in Google Flow Music. The release improves musicianship, lyrics, vocals, and creative control: it produces richer, more natural melodic structures; improves lyric quality, prompt adherence, and structure awareness; offers more expressive vocals with finer emotional detail and better pronunciation; and makes tempo and duration easier to control.
Google DeepMind has released Gemini 3.5 Live Translate, a near-real-time speech-to-speech translation audio model supporting more than 70 languages. It detects languages automatically and preserves the speaker's intonation, rhythm, and pitch.
Why it matters: Gemini 3.5 Live Translate replaces sentence-by-sentence waiting with continuous generation and offers developer, enterprise, and consumer deployment paths.
Google DeepMind has released Gemini 3.1 Flash TTS, a text-to-speech model focused on control, expressiveness, and audio quality. It is available in developer preview through the Gemini API and Google AI Studio, in enterprise preview on Vertex AI, and to Workspace users through Google Vids.
Why it matters: The official release explains how to use audio tags and lists language coverage, helping readers assess how controllable speech generation is.
Mistral AI has released Voxtral TTS, its first text-to-speech model. The 4B model supports nine languages—English, French, German, Spanish, Dutch, Portuguese, Italian, Hindi, and Arabic—and offers expressive emotion and low latency.
Why it matters: The source reports the 4B model's language coverage and 70 ms latency, and compares it with ElevenLabs, helping readers assess cost and usability for voice agents.
Mistral has released Voxtral Transcribe 2, with two speech-to-text models: Voxtral Mini Transcribe V2 for batch transcription and Voxtral Realtime for live use.
Why it matters: The source reports latency, pricing, and open-source licensing for both transcription models, helping readers assess options for real-time speech workloads.
Mistral has released Voxtral speech-understanding models in 24B and 3B sizes, both open-source under Apache 2.0 and available through an API. They support a 32K-token context, can transcribe up to 30 minutes of audio or understand up to 40 minutes, and provide built-in question answering and summarization, automatic multilingual detection, and speech-triggered function calls. Their text capabilities are inherited from Mistral Small 3.1.
Why it matters: Mistral's open speech-understanding models come in two sizes, under Apache 2.0, with API pricing disclosed, helping readers assess transcription and audio-understanding costs.
