Updated daily at 05:00 UTC
Speech-to-speech
Kimi-Audio
Open audio foundation model for speech recognition, audio understanding and spoken chat.
By Moonshot AI.
Versions
1 version
| Model | Maker | Kind | Released | Context | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|
| Kimi-Audio-7B-InstructKimi-Audio · Open weights | Moonshot AI | Speech-to-speech | 25 Apr 2025 | — | — | — |
