Bugs

To reproduce: navigate to Empathic voice interface -> playground -> select voice -> custom voice. Choose a female "base" voice, like Stella. Modify some parameter or leave them at defaults. Click the button to hear the voice. ACTUAL RESULT: the base voice selection is ignored, it's always the same male voice despite user selection. EXPECTED RESULT: the voice will in fact use the selected base voice.

To reproduce: navigate to Empathic voice interface -> playground -> select voice -> custom voice. Choose a female "base" voice, like Stella. Modify some parameter or leave them at defaults. Click the button to hear the voice. ACTUAL RESULT: the base voice selection is ignored, it's always the same male voice despite user selection. EXPECTED RESULT: the voice will in fact use the selected base voice.

To reproduce: navigate to Empathic voice interface -> playground -> select voice -> custom voice. Choose a female "base" voice, like Stella. Modify some parameter or leave them at defaults. Click the button to hear the voice. ACTUAL RESULT: the base voice selection is ignored, it's always the same male voice despite user selection. EXPECTED RESULT: the voice will in fact use the selected base voice.

Sometimes EVI will detect an interruption when there really isn't one (eg just background noise or the user backchanneling), and sometime it fails to recover from these false positive interruptions. We are working on improvements to reduce these issues.

Often EVI 2's words do not match the transcript exactly - it will say something that is not in the transcript, or mis-speak something that is in the transcript. We're currently working on preventing this.

It tends to twist words in text-to-text. For example "Craftsmanship" turns into "Scraftshipness".

Cannot Generate a Project - just started my 'Creator' account and cannot make one :( - see text for error I'm receiving. Message: Unable to create project. {"timestamp":"2025-03-06T10:16:37.012+00:00","status":400,"error":"Bad Request","message":"This user (user_id: 341720b3-13cb-4a17-b937-31f2c355a8da) already has 0 TTS Projects, and the maximum allowed is 0","path":"/projects"}

Integration with Twilio. When you listen to the recording, the user sounds like a chipmunk. This is not an issue when done through computer or App. Only Twilio phone calls.

HI Team can you please work on latency minimisation, so conversation should be very smooth, as right now we have to wait till it responds, it does not work when there is noise in the background.

During a conversation we want to update the System Prompt to guide the conversation more specifically. We do that using the session_settings Message. After a new System Prompt is active we need a way to interrupt the model gracefully so it starts responding in the context of the new System Prompt. We can trigger a new response using a User Input message with little or no content, but this will not clean up the current generation and playback gracefully. Suggestion: One way could be to have a flag in the session_settings message that signals EVI2 to gracefully clear generation and respond like a reconnect happened. Workaround: Reconnect manually with new System Prompt and Chat Resume feature