MoonshotAI/Kimi-Audio

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

4731 stars · 375 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity active

speech-recognition audio-processing machine-learning llm-inference tts speech-processing artificial-intelligence large-language-models python audio-foundation-model speech-conversation asr audio-understanding 7b-model moonshot-ai audio gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="MoonshotAI/Kimi-Audio")