Skip to main content
株式会社オブライト
Services
About
Company
Column
Glossary
Pricing
Free Tools
Contact
日本語
日本語
メニューを開く
Column
音声AI
Articles tagged "音声AI"
11 articles
AI
2026-11-17
ZONOS3-Mini: An Open 43-Language TTS with 100M Active Parameters — Requirements, Japanese Support and Voice Cloning [vs Irodori-TTS and Fish Audio]
ZONOS3-Mini is an open-weight TTS model from Zyphra with about 800M total and 100M active parameters. It supports 43 languages including Japanese and voice cloning, with Apache 2.0 weights. We cover official requirements and real file sizes for browser, NVIDIA, Mac and CPU, how to run it, and how it differs from Irodori-TTS, Fish Audio, VoiceStudio and ElevenLabs. Updated Nov 2026.
音声AI
ローカルAI
オープンソース
AI
2026-10-30
Nemotron 3.5 Transcribe Explained: NVIDIA's Prompt-Controlled ASR Model, Japanese Support and Setup (2026)
Nemotron 3.5 Transcribe is NVIDIA's prompt-controlled ASR model (34B MoE, 4.3B active). Japanese supported, OpenMDW-1.1 license, H100 80GB advised. Setup.
NVIDIA
音声AI
音声認識
Software Development
2026-10-16
What Is BetterWispr? Free Open-Source Dictation for Mac: Setup, Japanese Support, vs Wispr Flow
BetterWispr is a free Apache 2.0 Mac dictation app: hold Option+Space to type by voice. Local Parakeet/Whisper, requirements, Japanese, vs Wispr Flow.
オープンソース
開発ツール
Apache 2.0
AI
2026-10-15
Fish Audio Drama 3 Guide: Requirements, License and Usage
Fish Audio Drama 3 (Oct 2026): 35B MoE open-weight TTS. No official minimum; 48GB GPU advised. Free commercial use under $500K revenue, API cost, SGLang-Omni.
音声AI
Open Weight LLM
MoE
AI
2026-10-09
Whistle Explained: Cactus's 16.9MB Speech-to-Text Model
Whistle is Cactus's 16.9MB open speech-to-text model for CPU, Apache 2.0. It supports 7 languages but not Japanese. Speed vs Whisper base, setup, best uses.
音声AI
ローカルAI
オープンソース
AI
2026-10-01
Irodori-TTS-v4-Large Explained: A 3.29B Japanese TTS — Voice Cloning, Voice Design, Emoji Control, Differences from v4.1-Small, and License [Released September 2026]
Irodori-TTS-v4-Large is a 3.29B Japanese-only TTS with voice cloning, Voice Design and emoji control. Setup, benchmarks vs v4.1-Small, Gemma license notes.
音声AI
ローカルAI
Hugging Face
AI
2026-09-14
What Is VoiceStudio? The Fully-Local, Open-Source ElevenLabs Alternative
A guide to debpalash/VoiceStudio (formerly OmniVoice-Studio), which surged on GitHub Trending in September 2026. Covers how it runs voice cloning, voice design, video dubbing, dictation, transcription, and audiobook creation entirely on local hardware, its 16 TTS / 11 ASR engine lineup, installation, local API/MCP support, and how it compares to ElevenLabs and other tools.
音声AI
ローカルAI
オープンソース
AI
2026-09-13
GPT-Live-1 Guide: $0.05/min Full-Duplex Voice API Explained
GPT-Live-1 is OpenAI's full-duplex voice model, released Sep 10, 2026, billed $0.05/min on a dedicated Live endpoint, with 87% tool accuracy and 0.8s latency.
OpenAI
Realtime API
音声AI
AI
2026-05-08
OpenAI GPT-Realtime-2 and the Three New Voice Models — A Practitioner's 2026 Look at Reasoning Voice Agents, Live Translation, and Streaming Whisper
On May 7, 2026, OpenAI released a trio of new voice models: GPT-Realtime-2 (the first voice model with GPT-5-class reasoning), GPT-Realtime-Translate (live translation across 70+ input / 13 output languages), and GPT-Realtime-Whisper (streaming speech-to-text). This article summarizes capabilities, benchmark deltas vs 1.5, pricing, when to pick which, and the upgrade decision from 1.5 — based on official information.
OpenAI
gpt-realtime-2
Realtime API
AI
2026-04-28
OpenAI gpt-realtime-1.5 and the Official realtime-voice-component — A Practitioner's Look at the New Voice-Agent Stack [2026]
OpenAI released the gpt-realtime-1.5 audio model on February 26, 2026, and openai/realtime-voice-component on GitHub provides an official React reference for voice UIs. This article summarizes the documented gains (+5% audio reasoning, +10.23% transcription, +7% instruction following), pricing, the component's positioning as a reference implementation, and practical considerations for business adoption.
OpenAI
gpt-realtime
Realtime API
AI
2026-04-06
NVIDIA PersonaPlex 7B Complete Guide — Real-Time Full-Duplex Voice AI Architecture & Use Cases [2026]
NVIDIA PersonaPlex 7B, released in January 2026, is an open-source voice AI that integrates the traditional ASR→LLM→TTS pipeline into a single end-to-end model, achieving true full-duplex voice interaction. This guide covers architecture, performance benchmarks, setup procedures, and practical use cases.
PersonaPlex
NVIDIA
音声AI