litert-community/Kokoro-82M
text-to-speech model by litert-community
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.
Fully on-device, multilingual text-to-speech in a single file. This is hexgrad/Kokoro-82M (82M-parameter StyleTTS 2 + ISTFTNet) packaged as a .litertlm bundle for the MediaPipe Text-to-Speech (TextToSpeech) Task and LiteRT-LM, Google's open-source on-device inference runtime, across Android, iOS, macOS, Python, Web, and C++. Everything needed to turn text into 24 kHz speech is inside the one file: INT8 acoustic + vocoder models, all 54 voices, and self-contained text front-ends (text normalization and grapheme-to-phoneme) for 9 languages / dialects — no Python, no network, and no external GPL phoneme libraries, so the whole stack is Apache-2.0. Both files contain the same acoustic model weights, voices and text front-ends, and their vocoder graph is exported so that intermediate values stay inside the FP16 range (enabling native FP16 GPU execution, which roughly halves vocoder latency compared to FP32). The two files differ only in how the vocoder is quantized: delegate runs natively on OpenCL,…
Read the full model card ↗ · Preview checked 2026-11-10T06:57:32.323Z
Inside the original model card — Document outline
- Kokoro-82M for MediaPipe & LiteRT-LM
- Which file should I use?
- Download
- MediaPipe Text-to-Speech Task Capabilities
- Usage with MediaPipe Text-to-Speech Task
- 1. Android (Kotlin)
- Add the Gradle dependency
- Initialize the task and list voices
- Unary synthesis & word-level timestamps
- Streaming synthesis & incremental LLM-to-TTS streaming
- 2. iOS & macOS (Swift)
- Add the Swift Package
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
litert-community/Kokoro-82M is a text-to-speech model repository published by litert-community on Hugging Face. The source reports the litert-lm library.
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
- litert-lm
- Recent downloads (30 days)
- 35,304
- Cumulative likes
- 9
- Hugging Face trending score
- 1
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-07-07T02:27:31.000Z
- Last modified
- 2026-11-10T03:56:42.000Z
Compatibility and lineage
Reported languages: en, es, fr, it, pt, hi, zh, ja
Reported base models: hexgrad/Kokoro-82M
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 2026-11-14T06:59:51.921Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.