rand0wn/voice-eval

Document and test a Windows PowerShell quickstart about 1 hour ago

documentation good first issue priority: p2 area: docs

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Add optional OpenTelemetry tracing for evaluation and adapter execution about 1 hour ago

enhancement help wanted area: api difficulty: advanced area: adapters priority: p2

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Provide pytest fixtures and assertions for voice-agent evaluations about 1 hour ago

enhancement help wanted area: grading area: cli priority: p2 difficulty: intermediate

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Generate a self-contained HTML report with per-turn audio playback about 1 hour ago

enhancement help wanted priority: p2 difficulty: intermediate area: reports

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Add persistent API run storage and asynchronous evaluation jobs about 1 hour ago

enhancement help wanted area: api difficulty: advanced priority: p2

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Document opt-in credentialed smoke tests for real provider adapters about 1 hour ago

documentation help wanted priority: p1 area: ci area: adapters difficulty: intermediate

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Implement an OpenAI Realtime native speech-to-speech adapter about 1 hour ago

enhancement help wanted difficulty: advanced area: adapters priority: p2

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Add Ruff linting and formatting checks to contributor CI about 1 hour ago

enhancement good first issue area: ci priority: p2

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Add a synthetic interruption and barge-in evaluation scenario about 1 hour ago

enhancement good first issue area: scenarios priority: p2

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Add an optional pluggable LLM judge alongside deterministic grading about 1 hour ago

enhancement help wanted area: grading difficulty: advanced priority: p2

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Add a goal-driven simulated user for dynamic agent-to-agent evaluations about 1 hour ago

enhancement help wanted difficulty: advanced area: scenarios priority: p2

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Add a synthetic human-handoff and escalation scenario about 1 hour ago

enhancement good first issue area: scenarios priority: p2

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Add a CLI command to list available scenarios and adapters about 1 hour ago

enhancement good first issue area: cli priority: p2

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Handle .yaml and .yml scenario files consistently about 1 hour ago

bug good first issue area: scenarios priority: p1

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Add structured GitHub issue templates for bugs, adapters, and feature proposals about 1 hour ago

documentation good first issue priority: p2 area: docs

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Fix package and API version drift with one authoritative version source about 1 hour ago

bug good first issue area: cli area: api priority: p1

rand0wn/voice-eval

4

Simulation and grading module for voice AI pipelines: scripted multi-turn conversations, per-turn audio capture, rule-based grading, cross-pipeline comparison

Python

Open Issues Need Help