AgentPostmortem/Voiceeval

from_dict throws raw KeyError/ValueError on malformed turns 4 days ago

help wanted good first issue

0

Evaluation for voice agents. Catches what text evals cannot see: mis-hearing, missing confirmation, latency, barge-in. Everyone can demo a voice agent; this tells you if yours is getting worse.

Python

#ai-agents#evaluation#llm#python#speech-to-text#voice-ai

New check correction_ignored: flag actions on pre-correction values 8 days ago

help wanted good first issue

AgentPostmortem/Voiceeval

0

Evaluation for voice agents. Catches what text evals cannot see: mis-hearing, missing confirmation, latency, barge-in. Everyone can demo a voice agent; this tells you if yours is getting worse.

Python

#ai-agents#evaluation#llm#python#speech-to-text#voice-ai

New check repeat_loop: flag callers forced to repeat 3+ times 8 days ago

help wanted good first issue

AgentPostmortem/Voiceeval

0

Evaluation for voice agents. Catches what text evals cannot see: mis-hearing, missing confirmation, latency, barge-in. Everyone can demo a voice agent; this tells you if yours is getting worse.

Python

#ai-agents#evaluation#llm#python#speech-to-text#voice-ai

New check confirmed_wrong_value: flag confirmations echoing the misheard number 8 days ago

help wanted good first issue

AgentPostmortem/Voiceeval

0

Evaluation for voice agents. Catches what text evals cannot see: mis-hearing, missing confirmation, latency, barge-in. Everyone can demo a voice agent; this tells you if yours is getting worse.

Python

#ai-agents#evaluation#llm#python#speech-to-text#voice-ai

New check sensitive_readback: flag full card/SSN numbers spoken aloud 8 days ago

help wanted good first issue

AgentPostmortem/Voiceeval

0

Evaluation for voice agents. Catches what text evals cannot see: mis-hearing, missing confirmation, latency, barge-in. Everyone can demo a voice agent; this tells you if yours is getting worse.

Python

#ai-agents#evaluation#llm#python#speech-to-text#voice-ai

Negative/out-of-order clocks silently pass check_latency 13 days ago

help wanted good first issue

AgentPostmortem/Voiceeval

0

Evaluation for voice agents. Catches what text evals cannot see: mis-hearing, missing confirmation, latency, barge-in. Everyone can demo a voice agent; this tells you if yours is getting worse.

Python

#ai-agents#evaluation#llm#python#speech-to-text#voice-ai

help wanted good first issue

AgentPostmortem/Voiceeval

0

Evaluation for voice agents. Catches what text evals cannot see: mis-hearing, missing confirmation, latency, barge-in. Everyone can demo a voice agent; this tells you if yours is getting worse.

Python

#ai-agents#evaluation#llm#python#speech-to-text#voice-ai

_CONFIRM misses the natural Confirmed phrasing (false no_confirmation) 13 days ago

help wanted good first issue

AgentPostmortem/Voiceeval

0

Evaluation for voice agents. Catches what text evals cannot see: mis-hearing, missing confirmation, latency, barge-in. Everyone can demo a voice agent; this tells you if yours is getting worse.

Python

#ai-agents#evaluation#llm#python#speech-to-text#voice-ai

check_policy_violation ignores string amounts 13 days ago

help wanted good first issue

AgentPostmortem/Voiceeval

0

Evaluation for voice agents. Catches what text evals cannot see: mis-hearing, missing confirmation, latency, barge-in. Everyone can demo a voice agent; this tells you if yours is getting worse.

Python

#ai-agents#evaluation#llm#python#speech-to-text#voice-ai

Add a test for an untested edge case about 1 month ago

good first issue

AgentPostmortem/Voiceeval

0

Evaluation for voice agents. Catches what text evals cannot see: mis-hearing, missing confirmation, latency, barge-in. Everyone can demo a voice agent; this tells you if yours is getting worse.

Python

#ai-agents#evaluation#llm#python#speech-to-text#voice-ai

Add a copy-paste quickstart to the README about 1 month ago

good first issue

AgentPostmortem/Voiceeval

0

Evaluation for voice agents. Catches what text evals cannot see: mis-hearing, missing confirmation, latency, barge-in. Everyone can demo a voice agent; this tells you if yours is getting worse.

Python

#ai-agents#evaluation#llm#python#speech-to-text#voice-ai

Digit-level confusions are missing, and those are the ones on card and account numbers about 1 month ago

enhancement good first issue

AgentPostmortem/Voiceeval

0

Evaluation for voice agents. Catches what text evals cannot see: mis-hearing, missing confirmation, latency, barge-in. Everyone can demo a voice agent; this tells you if yours is getting worse.

Python

#ai-agents#evaluation#llm#python#speech-to-text#voice-ai

The mishearing and confirmation vocabularies are hardcoded English, so a non-English call reports zero findings about 1 month ago

enhancement help wanted

AgentPostmortem/Voiceeval

0

Evaluation for voice agents. Catches what text evals cannot see: mis-hearing, missing confirmation, latency, barge-in. Everyone can demo a voice agent; this tells you if yours is getting worse.

Python

#ai-agents#evaluation#llm#python#speech-to-text#voice-ai

Open Issues Need Help