second-state / echokit_server
Open Source Voice Agent Platform
Why this job: says: voice agent; topics: tts, asr, voice-assistant
What it does
- ASR (Speech Recognition). Works with any API that’s *OpenAI-compatible*.
- LLM (Language Model). Connect to any *OpenAI-spec* endpoint — local or cloud.
- TTS (Text-to-Speech). Use any *OpenAI-spec* voice model for flexible deployment.
- Gemini. Google’s multimodal model
- Qwen Real-Time. Alibaba’s powerful open LLM
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Inactive
- Last commit 9 months ago
- Stars
- 590
- On GitHub
- Licence
- GPL-3.0
- Share-alike terms
- Downloads for
- Linux
- From the latest release
- Latest version
- v0.3.2
- Released 9 months ago
- Built with
- Rust
- 63% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 20% closed
- 16 still open
- Pull requests
- 21 merged
- 6 waiting
- Releases
- 13
- 8 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| zai-org / GLM-ASR | 861 | 8 months ago | Apache-2.0 | No downloads |
| mbailey / voicemode | 1,452 | 4 days ago | MIT | No downloads |
| wwbin2017 / bailing | 1,795 | 7 months ago | MIT | No downloads |
More: download files, languages, topics and project record
Languages
- Rust 63%
- HTML 37%
- Dockerfile <1%
Topics
- agentic-ai
- ai
- asr
- esp32
- llm
- mcp
- mcp-client
- tts
- voice
- voice-assistant
Project record
- JobSpeech and audio
- StatusListed
- Commits306
- Forks77
- Watching7
- Stars in 28 days+1
- CreatedFeb 26, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026