Meeting Summary Service

Source: 10_meeting_summary_service

An HTTP server that accepts raw audio uploads, transcribes them with the ElevenLabs Scribe API, generates a structured meeting summary with Claude Sonnet, and streams the summary back as the HTTP response. Each request is handled in its own track — the server processes multiple simultaneous uploads without any explicit thread management.

Running

melodium run 10_meeting_summary_service/Compo.toml \
  --anthropic_key sk-ant-... \
  --elevenlabs_key el-...

$ curl -X POST http://127.0.0.1:8080/summarise \
       --data-binary @meeting.wav \
       -H "Content-Type: audio/wav"
## Meeting Summary
 
**Overview:** …
 
**Key decisions:**
- …
 
**Action items:**
- …

How it works

Three models are instantiated at startup:

model server: HttpServer(…)
model stt:    Stt(elevenlabs_key=elevenlabs_key)
model llm:    Llm(anthropic_key=anthropic_key)

Stt uses the ElevenLabs scribe_v1 model. Llm uses Claude Sonnet with a structured summarisation system prompt and a lower temperature (0.4) to produce focused, consistent output.

Per-request pipeline

The summariseRequest sub-treatment handles everything for one request:

transcribe returns a Block<string>. The stream<string>() adapter converts it to a Stream<string> so it can flow into buildSummaryPrompt, which wraps the raw transcript in a prompt template using entry + format.

chat returns a Stream<string> of response tokens, which are encoded and forwarded directly into connection.data — summary tokens appear in the HTTP response as they are generated.

Video Explanation

Dependencies

[dependencies]
std      = "0.10.1"  # core flows, logging, data structures
http     = "0.10.1"  # HTTP server and client
net      = "0.10.1"  # IP address helpers
encoding = "0.10.1"  # UTF-8 encode / decode
ml       = "0.10.1"  # LLM, STT, TTS and local model inference