Inflect is a lightweight, high‑quality text‑to‑speech model designed to deliver surprisingly natural audio with a minimal footprint. It’s an active work‑in‑progress focused on fast iteration, strong voice quality, and simple integration for developers experimenting with modern TTS systems.
☆166Jul 26, 2026Updated 3 months ago
Alternatives and similar repositories for Inflect
Users that are interested in Inflect are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official repository for “GrainSpeech: Less Context, More Detail for Compact Speech Synthesis.”☆59Sep 18, 2026Updated last month
- CuteTTS: a lightweight continuous autoregressive TTS model that runs efficiently on GPUs, CPUs, and Apple silicon.☆83Aug 25, 2026Updated 2 months ago
- Open-weights speaker diarization for pyannote.audio 4.x: WavLM-Base+ / Conformer segmentation + SimAM-ResNet34 embeddings, by Reway.☆23Sep 10, 2026Updated last month
- Extract a target speaker’s clean, non-overlapped speech from multi-speaker audio and export word-safe LJSpeech-style TTS datasets.☆24Jun 14, 2026Updated 4 months ago
- An always-listening turn detector for voice agents, small enough to run on every 20 ms of audio.☆15Oct 15, 2026Updated 3 weeks ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Natural-sounding streaming text-to-speech for the ESP32-S3: 3.3 M params, 3.8 MB of weights, no cloud, no NPU☆32Updated this week
- Synthetic data augmentation technique via LLM for Automatic Speech Recognition fine tuning.☆10Oct 4, 2025Updated last year
- ☆27Jul 3, 2026Updated 4 months ago
- Ultra-tiny 2.1k streaming voice activity detector (2.1 KB INT8). 200 ms window for microcontrollers, edge devices, and DSPs. ships with O…☆65Sep 9, 2026Updated last month
- A highly optimized engine for neutts-air model to generate minutes of audio in seconds. Over 200x realtime on modern hardware!☆119Nov 24, 2025Updated 11 months ago
- ☆33Updated this week
- This project provides a complete, documented training recipe for fine-tuning Kokoro-82M on a new language. In this case German☆138Jun 29, 2026Updated 4 months ago
- Official implementation of ACL'26 (findings) paper WESR (Word-level Event-Speech Recognition): A comprehensive benchmark and baseline for…☆48Jan 30, 2026Updated 9 months ago
- Open-weights voice acting pipeline combining zero-shot voice cloning with natural-language direction. Provide a reference voice (or gener…☆18May 25, 2026Updated 5 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Nar TTS: high-throughput Qwen3 + Mimi text-to-speech☆22Aug 21, 2026Updated 2 months ago
- A simple, hackable text-to-speech system in PyTorch and MLX☆190Aug 3, 2025Updated last year
- ☆60Feb 8, 2026Updated 8 months ago
- Soprano-Factory: Train your own 2000x realtime text-to-speech model☆262Jan 13, 2026Updated 9 months ago
- Official implementation of “TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech Synthesis"(ACL-26).☆14May 18, 2026Updated 5 months ago
- Kanade is a single-layer disentangled speech tokenizer that extracts compact tokens suitable for both generative and discriminative model…☆120Jul 18, 2026Updated 3 months ago
- The inference and trainging code for WordVoice.☆75Aug 21, 2026Updated 2 months ago
- ☆12Jun 24, 2026Updated 4 months ago
- FlashFunAsr: A lightweight vLLM implementation built from scratch for FunASR nano☆12Jan 5, 2026Updated 10 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-Speech Synthesis☆27Mar 21, 2025Updated last year
- High fidelity neural audio codec for TTS models☆37Dec 22, 2025Updated 10 months ago
- Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation☆78Jun 16, 2026Updated 4 months ago
- Repo for Paper: Towards Robust Speaker Recognition against Intrinsic Variation with Foundation Model Few-shot Tuning and Effective Speech…☆11Sep 24, 2025Updated last year
- ☆12Updated this week
- Preference-supervised naturalness scorer for modern neural TTS . best way to measure naturalness☆21May 29, 2026Updated 5 months ago
- Official implementation of paper "Vocoder is not all you need".☆17Jul 20, 2026Updated 3 months ago
- Training code for kokoro tts model☆47Nov 15, 2025Updated 11 months ago
- ☆165Oct 15, 2026Updated 3 weeks ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Customized Seed-VC implementation☆14Updated this week
- Lightweight self-hosted chat interface for OpenAI-compatible APIs and local models.☆33Oct 22, 2026Updated 2 weeks ago
- An attempt to reproduce CALM (Continuous Audio Language Models) using DACVAE as the audio VAE.☆20Feb 20, 2026Updated 8 months ago
- Extract voice style embeddings from any WAV for SupertonicTTS — no style encoder needed.☆61Sep 5, 2026Updated 2 months ago
- On-device voice isolation, wake words, voice activity and voiceprints. In the browser (WebAssembly), Python, Android and iOS, with plugin…☆69Updated this week
- supertonic for nvda☆10Jul 22, 2026Updated 3 months ago
- Echo-TTS inference codebase☆230Dec 5, 2025Updated 11 months ago