# MoonshotAI/Kimi-Audio

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

Repository: https://github.com/MoonshotAI/Kimi-Audio
Canonical: https://ross.abutalabs.com/products/kimi-audio
Language: Python
License Family: other
Last push: 2025-06-21T15:30:28+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 27, release rhythm 35, longevity 35
- inputs: {"age_days": 495, "days_push": 438, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4731, forks 375 (observed 2026-08-28T04:08:57.671553+00:00)

## What it is
Kimi-Audio is an open-source audio foundation model (7B parameters) that unifies audio understanding, generation, and speech conversation in a single framework. The repository provides inference code, pretrained and instruct model weights, finetuning examples, and an evaluation toolkit.

## Use cases
- transcribe speech to text with a single model
- build a voice chat assistant that listens and responds
- answer questions about audio clips
- classify emotions or sound events from audio
- caption audio recordings automatically
- finetune an audio LLM on custom data

## When to choose
- you need one model covering ASR, audio QA, captioning, emotion recognition, and speech conversation
- you want state-of-the-art open weights for audio understanding benchmarks
- you want to finetune a large audio foundation model

## When to avoid
- you need a lightweight production ASR with low latency on CPU
- you need a permissively licensed model - the repo has no license file
- you only need simple text-to-speech without understanding

## Facets
- artifact type: library
- maturity: active
- function: speech-recognition, audio-processing, machine-learning, llm-inference, tts
- domain: speech-processing, artificial-intelligence, large-language-models
- platform: python
- tags: audio-foundation-model, speech-conversation, asr, audio-understanding, 7b-model, moonshot-ai, audio, gpu, linux

## Member repositories
- MoonshotAI/Kimi-Audio (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:57.671553+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:19:00.817137+00:00, confidence not recorded.
  - readme: https://github.com/MoonshotAI/Kimi-Audio (fetched 2026-08-28T04:08:57.671553+00:00, sha d6e3433d9408)
- Data as of 2026-08-30T08:39:29.467469+00:00.