Voxtral: Open-Weights TTS Alternative to ElevenLabs by Mistral
Mistral releases Voxtral, a 4B-parameter open-weights TTS model with 70ms latency, 3s voice cloning, 9 languages, and strong ElevenLabs results.
An open alternative to ElevenLabs with open weights has appeared.
Voxtral is a speech synthesis (text-to-speech) model from Mistral:
- only 4 billion parameters
- 70 ms latency for voice agents
- voice cloning from 3 seconds of audio
- 9 languages + cross-lingual transfer
- 68.4% wins compared to ElevenLabs Flash v2.5
Comments
Weekly digest
The best of vibe coding, AI agents and open source — once a week, no spam.
Related articles
All articlesDigUp: EmbeddingGemma 2 Powered Local Search App for macOS
DigUp uses Google’s open‑source EmbeddingGemma 2 to deliver fast, on‑device search of files, PDFs, photos, podcasts and videos on macOS.
OpenAI expands GPT‑6.1 context window to 500k tokens by default
OpenAI raised the default context window of GPT‑6.1 in Codex and ChatGPT Work from 272k to 500k tokens, with plans for further expansion.
Animator: AI-Powered Hand‑Drawn Video Generator from Text Prompts
Animator creates narrated hand‑drawn animation videos from a simple text prompt in seconds, generating script, scenes, narration and icons via Python.