speech-generation

Official implementation of VQMIVC: One-shot (any-to-any) Voice Conversion @ Interspeech 2021 + Online playing demo!

CEP is a software platform designed for users that want to learn or rapidly prototype using standard A.I. components.

An end-to-end speech-to-speech language model that generates spoken responses without text guidance

Ultrafast Qwen3-TTS: sub-50 ms time-to-first-audio at 10 requests per second.

A fast speech-to-speech & speech-to-text translation model that supports simultaneous decoding and offers 28× speedup.

《SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts》

[ACL 2024] Generative Pre-Trained Speech Language Model with Efficient Hierarchical Transformer

Swift library for offline text-to-speech synthesis on iOS/macOS. Generate natural speech directly on device using CoreML-optimized FastPitch and HiFiGAN models. No internet required, fully private.

Self-supervised Generative LM-based Voice Conversion

Zero-shot voice cloning text-to-speech (TTS) with explicit emotion class conditioning built on F5-TTS

Unified toolkit for testing and comparing multiple state-of-the-art open-source Text-to-Speech (TTS) models (with voice cloning, multilingual support, and audio samples).

[CVPR 2026 Findings] DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization

A conversational speech model (CSM) that generates natural-sounding speech with context awareness and consistent audio quality. Supports multi-speaker conversations and maintains contextual understanding across turns, ensuring consistent audio output throughout the conversation.

Local-first AI media generation and video editing toolkit for coding agents, with a Bun CLI, TypeScript SDK, MCP server, and Agent Skill.

Streamlit frontend for Coqui-tts

Sprach-DNA-Extraktion & Reden-Generator: Claude Code Skill der den individuellen Redestil aus Beispielreden extrahiert, quantifiziert (47 Dimensionen) und reproduzierbar neue Reden generiert. Mit Feedback-Lernschleife und Skill-Selbstverbesserung.

Text-to-speech algorithm with continuous diffusion for categorical data

A unified interface to extract hidden representations from various speech foundation models

[Interspeech 2026] DiFlow-TTS: Compact and Low-Latency Zero-Shot Text-to-Speech with Discrete Flow Matching