tts

Violin is an open-source video translation tool that integrates speech recognition, large language model translation, and text-to-speech. It supports over 30 languages and offers three usage modes: CLI, web app, and Claude Code.

Violin is an open-source video translation skill that combines speech recognition, LLM translation, and speech synthesis into a seamless pipeline, supporting multilingual ASR, personalized translation, and interactive chat with video content.

DramaBox is an open-weight TTS model fine-tuned from LTX-2.3 that uses stage directions as prompts to generate expressive speech, with optional voice cloning from a 10-second sample.

Supertonic is a lightning-fast, on-device TTS model with 99M parameters, supporting 31 languages. It runs locally with no API costs, outperforms cloud TTS on accuracy for numbers, phone numbers, and technical terms, and can be installed via Python, Node.js, Rust, Go, and more.

OmniVoice Studio is an open-source desktop app that enables local voice cloning and cinematic video dubbing across 646 languages, fully offline with no API keys, positioning itself as a privacy-focused alternative to ElevenLabs.

Dramabox is an expressive text-to-speech model by Resemble AI that uses prompt-driven control for speaker identity, emotion, and delivery, with optional voice cloning via a 10-second reference. Built on the LTX-2.3 audio diffusion transformer, it is open-sourced on Hugging Face.

VoxCPM2 is an open-source, tokenizer-free diffusion autoregressive Text-to-Speech model supporting 30 languages with 2B parameters, 48kHz audio output, and features including voice design from natural language descriptions, controllable voice cloning, and real-time streaming capabilities.

Alibaba's Qwen team releases Qwen3-TTS-12Hz-1.7B-CustomVoice, a powerful text-to-speech model supporting 10 languages with low-latency streaming, instruction-based voice control, and robust contextual understanding.

This tutorial showcases a completely new way to make videos: without any text-to-video model, Claude generates dynamic graphics, sound effects, and narration directly frame by frame using native JavaScript — combined with a free database of 86 style prompts, Gemini TTS voiceover, and word-level timestamped subtitles — producing a finished video that doesn't look AI-generated at all.

LiveKit Agents is an open-source framework for building realtime, multimodal voice agents that can see, hear, and understand, with flexible STT/LLM/TTS integrations, job scheduling, telephony support, MCP compatibility, and a built-in test framework.

Kyutai releases Pocket TTS, a lightweight text-to-speech model that runs efficiently on CPUs with 100M parameters, low latency, and voice cloning, supporting multiple languages.

Voicebox is an open-source, local-first AI voice studio for voice cloning, speech generation, dictation, and AI agent integration, offering privacy and multi-engine TTS support.

Kokoro-82M is an efficient, high-quality text-to-speech model available on Replicate, supporting multiple languages and voices with low inference cost.

OpenAI’s new Codex desktop app combines code generation, browser automation and persistent agents into a single IDE, while Anthropic upgraded Claude Code with parallel sessions and Google launched desktop apps, Chrome slash commands and an expressive TTS model.

Anthropic, Alibaba, Google and others unleash a wave of major model drops—Claude Opus 4.7, Qwen 3.6, emotion-rich Google TTS, plus tiny 1.58-bit phone LLMs and real-time 3-D world generators—alongside open tools for video, VR and character creation.