Category

CohereLabs/cohere-transcribe-arabic-07-2026

Transcribes Arabic speech to text using a CohereLabs-trained ASR model compatible with the Hugging Face Transformers pipeline. Provides safetensors weights, endpoint compatibility and a DOI-tagged release; suitable for Arabic transcription workflows but may require adaptation for diverse dialects or noisy audio.

Gepard

Generates streaming, low‑latency neural speech for real‑time dialogue by autoregressively producing audio frames as text arrives; joint text–speech training preserves natural prosody. Optimized for vLLM streaming (~50 ms first chunk), supports short‑clip voice cloning and four languages.

Inflect-Micro-v2

Local English text-to-waveform TTS producing a single fixed synthetic voice in a deployable package below 10M parameters. Offers deterministic seeds, punctuation-aware long-text chunking, CPU/CUDA and ONNX runtime options, measured evaluations and a compact FP32 footprint; English-only, one voice.

Inflect-Nano-v2

Generates English speech locally from text into 24 kHz waveforms with a fixed synthetic male voice. Complete text-to-waveform TTS under ~4M parameters (≈16 MB FP32), supports CPU/CUDA inference, deterministic seeds, long-text chunking and an ONNX export path under Apache-2.0 license.

Hex

Turns speech into text in whichever app is active: hold a shortcut, speak, and release. Transcription runs locally after the speech model is downloaded, keeping routine dictation on your device.

VibeVoice-ASR-BitNet

Multilingual, real-time ASR for edge CPUs that uses heterogeneous quantization to reduce model size (4.62→1.58 GB) and lower inference latency. Trades some accuracy for 1.6–2.3× faster inference vs. Whisper.cpp and real-time capability on a few CPU threads, making it suitable for memory- and compute-constrained on-device transcription.

Audio8 TTS Preview 0.6B

Multilingual neural text-to-speech model (0.6B params) with zero-shot voice cloning and a bundled 44.1 kHz codec. Preview release targets 11 recommended languages and aims to deliver near-SOTA quality in a compact checkpoint suited for voice cloning and multilingual TTS prototypes.

NVIDIA NemotronLabs VoiceChat 11B

An end-to-end 11B full-duplex speech model for real-time conversational AI that jointly performs streaming speech understanding and generation, enabling ~450 ms turn-taking, barge‑in and live tool calling in a single unified architecture; research use only.

MiniMax Music 3

Generates complete songs (up to five minutes) from lyrics and a music description, producing 32 kHz stereo WAV with expressive vocals and long-range musical structure. Uses hierarchical LLMs fused with flow-matching/Flow-VAE synthesis for coherent arrangement and timbre; requires CUDA and integrates with Diffusers and SGLang-Omni.

AuK: An Open-Source Foundational Model for Speech Generation and Editing

Generates and edits speech from natural-language instructions plus optional reference audio, supporting zero-shot TTS, content/acoustic/paralinguistic edits, enhancement, and source separation. Open-source 1.5B-parameter base model with a 4-step distilled AuK‑Flash for faster inference.

Audio8 TTS Preview 0.1B

Zero-shot multilingual text-to-speech checkpoint for speech generation and voice cloning with a compact footprint. Features an ~170M-parameter main model plus a bundled ~120M-parameter codec decoder, with primary support for Chinese and English; other languages show more variable quality and long/noisy references reduce fidelity.

Breeze TTS 2

Generates low-latency, instruction-driven English and Chinese speech for voice cloning, voice design, and directed performances; supports real-time streaming, reference-free voice creation, and reference-guided cloning. Open-weight PyTorch model released under a research/non-commercial license with GPU recommendations.