by lukeocodes · AI 工具 · ★ 6
CompositeVoice An SDK for building AI voice agents — wire together any combination of input, STT, LLM, TTS, and output providers behind one unified 5-role pipeline. Why CompositeVoice? Building a voice agent from scratch means solving many hard problems simultaneously: microphone capture, WebSocket reconnection, turn-taking logic, interleaving STT/LLM/TTS lifecycles, and stitching together provider SDKs that share nothing in common. It is easy to spend weeks before your first working demo. CompositeVoice handles the plumbing. You declare the pipeline; the SDK runs it. | Feature
| Stars | 6 |
| Forks | 2 |
| Language | TypeScript |
| Category | AI 工具 |
| License | MIT |
| Quality Score | 33.75/100 |
| Last Updated | 2026-03-24 |
| Created | 2025-10-18 |
| Platforms | browser, gemini, node |
| Est. Tokens | ~10459k |
These tools work well together with composite-voice for enhanced workflows:
Explore other popular ai 工具 tools:
composite-voice is Composite voice agent SDK with no extra infra requirements. Supports browser-native STT/TTS features.. It is categorized as a AI 工具 with 6 GitHub stars.
composite-voice is primarily written in TypeScript. It covers topics such as ai-sdk, anthropic, assemblyai.
You can find installation instructions and usage details in the composite-voice GitHub repository at github.com/lukeocodes/composite-voice. The project has 6 stars and 2 forks, indicating an active community.
composite-voice is released under the MIT license, making it free to use and modify according to the license terms.