FluidInference/kokoro-82m-coreml
text-to-speech model by FluidInference
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Core ML conversions of hexgrad/Kokoro-82M (English and Japanese) and hexgrad/Kokoro-82M-v1.1-zh (Mandarin). The original Kokoro models and pretrained weights are by hexgrad; this repository provides Apple Core ML conversions and runtime optimizations. See FluidAudio for inference. Available for English, Japanese and Mandarin, with fixed Albert/decoder buckets, native source DSP and a GPU generator adapted from Matt Mireles's conversion. Existing model paths and defaults remain available. Use KokoroAneManager(version: .v3) for English, KokoroAneManager(variant: .japanese, version: .v3) for Japanese, or KokoroAneManager(variant: .mandarin, version: .v3) for Mandarin. All three accept native text and variant voices. Existing callers retain .legacy. See SDK usage, voices and platform limits. Requires macOS 15 / iOS 18; physical iOS inference remains unvalidated. The SDK pins model release 6c0750dd02ef9d981fb82f147d784a3f171755ee and base revision 006395f65025af251858b1ab0a7178a6a1e73f9f, adopting fp32 KokoroProsodyv2 and COLA-corrected KokoroTailv2. The bundled standalone conversion runtime and its historical measurements below are separate from this SDK integration. This documentation update does not change…
Read the full model card ↗ · Preview checked 2026-10-29T06:51:47.135Z
Inside the original model card — Document outline
- ANE version 3 (opt-in)
- FluidAudio SDK v0.17.6
- SDK compute routing and selected measurements
- Changelog
- Historical M4 Pro benchmark
- Kokoro-82M PyTorch (CPU)
- Kokoro-82M PyTorch (MPS)
- Kokoro-82M MLX Pipeline
- Swift + Fluid Audio Core ML models
- Credtis
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
FluidInference/kokoro-82m-coreml is a text-to-speech model repository published by FluidInference on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-speech
- Library
- Not reported
- Recent downloads (30 days)
- 13,576
- Cumulative likes
- 14
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2025-09-08T06:19:05.000Z
- Last modified
- 2026-10-28T23:17:32.000Z
Compatibility and lineage
Reported languages: en, ja, zh
Reported base models: hexgrad/Kokoro-82M, hexgrad/Kokoro-82M-v1.1-zh
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-29T06:50:43.795Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.