Voxtral ASR & TTS running natively and in the browser. A Rust implementation of Mistral's Voxtral mini realtime ASR / TTS using the Burn ML framework

Turn PDFs and EPUBs into audiobooks; subtitles or videos into dubbed videos (including translation), and more. For free. Pandrator uses local models, including voice-cloning (instant, RVC-enhanced, XTTS fine-tuning) and LLM processing. It aspires to be a user-friendly app with a GUI, an installer and all-in-one packages.

C++ ggml runtime hub for multilingual ASR models: Cohere Transcribe, Parakeet TDT, Voxtral, Canary 1B v2, etc, plus universal forced alignment via NeMo Forced Aligner-style CTC, and others. Fork of whisper.cpp.

Super STT enables effortless voice-to-text in any application, using the most advanced speech models.

Offline Speech-to-Text (STT) service using Mistral's Voxtral model with Wyoming protocol compatibility for Home Assistant Assist integration.

Voxtral is a state-of-the-art model developed to handle both speech transcription and audio understanding with remarkable accuracy and efficiency. This demo interface lets you run the Voxtral model on powerful GPUs to evaluate its performance and see how it can be used for transcription and deeper analysis.

Effortless Push-to-Talk Transcription, Anywhere.

A Web UI for easy subtitle using various models including voxtral

speech to text gui for different (e.g. Whisper, Voxtral) models and backends, including whisper.cpp, crispasar, mlx-whisper, faster-whisper, ctranslate2; applies pyannote for diarization

Voxtral Codec : Combining Semantic VQ and Acoustic FSQ for Ultra-Low Bitrate Speech Generation (Voxtral TTS Backbone)

Professional local-first AI production pipeline for long-form narration. Clone voices and generate studio-grade audiobooks (M4B/MP3) using Coqui XTTS-v2 and support for Voxtral (cloud)

Experimentation with Voxtral-Mini-4B-Realtime-2602 and DeepL API for live translation

github mirror for radioshaq - ham radio full time quarterback and part-time lobster

Enterprise-grade speech-to-text toolkit with pluggable backends (Whisper, Voxtral). Features speaker diarization, 80%+ test coverage, CI/CD quality gates, and fully offline operation.

Local implementation for voxtral

Real-time cloud-based speech-to-text for Windows. Powered by Mistral's realtime transcription API

🐝 Telegram AI agent designed for distracted users (like drivers). Powered by ElevenLabs, Voxtral, and a fine-tuned Ministral 3B using Nvidia Brev!

🔊 Streamline audio processing with Voxtral.c, a pure C implementation for Mistral AI's Voxtral 4B model, featuring real-time transcription and low memory use.

Desktop studio for local and remote Voxtral TTS with preset voices, Mistral API support, export controls, and a premium resizable UI.

Real-time phone scam detection powered by Mistral's Voxtral Mini - analyzes live audio and transcripts to identify fraud patterns