Analytics

Speaknode captures detailed data about every conversation for analysis and monitoring.

Conversation History

Every agent session is recorded with:

• Session metadata — agent, caller, start/end time, duration, status
• Audio recording — full session audio stored in object storage
• Transcription — text transcript of the conversation
• Telemetry spans — detailed OpenTelemetry traces of every step

Session List

Browse all conversations with filters:

• By agent
• By status (completed, failed, active)
• By date range
• By caller information

Session Detail

For each session you can view:

• Full conversation transcript with turn-by-turn breakdown
• Audio playback with waveform visualization
• Timing metrics per turn (latency, duration)
• Tool calls made during the session
• Error details (if failed)

Live sales analysis

The same machinery applies to recordings of human sales calls: an uploaded recording becomes a dialogue with roles and is scored against a set of characteristics — talk share, script compliance, objection handling, whether a next step was agreed.

• Upload — audio, audio with a ready transcript, or a transcript alone; in batches or as a ZIP archive from your telephony provider
• Transcription with diarization — an external service splits the recording into utterances with roles and timecodes
• Characteristics — computed metrics come from the backend, judged ones from a language model, every score carrying a justification and a quote
• Reports — aggregations by rep, by date, by company; saved views and a team dashboard

Agent conversations and human recordings live in the same entity and are measured by the same metrics — a bot and a live rep compare directly.

See Call Analytics for details.

Telemetry & Tracing

The platform uses OpenTelemetry for end-to-end tracing:

User speaks → STT span → LLM span → Tool call span → TTS span → User hears

Each conversation is a trace containing spans for every operation:

• Span name — operation type (STT, LLM inference, tool call, TTS)
• Duration — how long each step took
• Status — success or error
• Attributes — tags and metadata
• Events — detailed events within the span

Telemetry Pipeline

Python Worker → OTEL Collector → Kafka → ASP.NET Consumer → Database
                                      → Langfuse (internal observability)

Data Storage