Speech-to-text pipeline template

Components in this data flow diagram

• Call recordings & meeting audio
• Object storage: raw audio
• Convert to 16 kHz mono WAV: FFmpeg
• Voice activity detection
• Speech detected?
• Mark as silent & skip
• Chunk into 30 s segments
• ASR model: OpenAI Whisper
• Speaker diarisation: pyannote
• Align words with speakers & timestamps
• Punctuation & casing
• Contains card numbers or PII?
• Redact text & bleep audio
• Transcript store
• Elasticsearch full-text index
• LLM summary & action items
• Push notes to CRM
• Sample for word-error-rate QA

How to use this data flow diagram template

1. Click Open in the editor. The data flow diagram opens on a new page in FlowDiagram — nothing is uploaded and there is no sign-up.
2. Rename, add or delete shapes and drag them where you want; connectors stay attached as things move.
3. Drop in vendor logos from the library — 1,160 of them, including every AWS, Azure and Google Cloud service icon — or restyle it with the colour and theme controls.
4. Prefer text? Edit the Mermaid source below and paste it in through ☰ → Import diagram (see the Mermaid editor); it imports as an editable diagram.
5. Export to PNG, SVG or PDF, or press Ctrl+L for a link that carries the whole diagram.

Mermaid source

The whole template is the text below. Paste it into FlowDiagram, keep it in Git next to the code it describes, or hand it to an AI assistant to extend.

flowchart LR
  AUDIO[Call recordings & meeting audio] --> STORE[(Object storage: raw audio)]
  STORE --> CONVERT[Convert to 16 kHz mono WAV: FFmpeg]
  CONVERT --> VAD[Voice activity detection]
  VAD --> SPEECH{Speech detected?}
  SPEECH -->|No| SKIP[Mark as silent & skip]
  SPEECH -->|Yes| CHUNK[Chunk into 30 s segments]
  CHUNK --> ASR[ASR model: OpenAI Whisper]
  CHUNK --> DIAR[Speaker diarisation: pyannote]
  ASR --> ALIGN[Align words with speakers & timestamps]
  DIAR --> ALIGN
  ALIGN --> PUNCT[Punctuation & casing]
  PUNCT --> PII{Contains card numbers or PII?}
  PII -->|Yes| REDACT[Redact text & bleep audio]
  PII -->|No| TRANSCRIPT[(Transcript store)]
  REDACT --> TRANSCRIPT
  TRANSCRIPT --> SEARCH[Elasticsearch full-text index]
  TRANSCRIPT --> LLM[LLM summary & action items]
  LLM --> CRM[Push notes to CRM]
  TRANSCRIPT --> WER[Sample for word-error-rate QA]

Related: Data pipeline diagram tool · Mermaid editor · All ai & ml pipelines templates · All 521 templates