librechat.yaml
doesn't recognize speech
settings at root level.
#4084
-
What happened?I am trying to configure STT via Steps to ReproduceWhen I place the following snippet in
I am not getting speech working, please see error logs below. What browsers are you seeing the problem on?Chrome Relevant log output{
"issues": [
{
"code": "unrecognized_keys",
"keys": [
"speech"
],
"message": "Unrecognized key(s) in object: 'speech'",
"path": []
}
],
"level": "error",
"message": "Invalid custom config file at /app/librechat.yaml [
{
\"code\": \"unrecognized_keys\",
\"keys\": [
\"speech\"
],
\"path\": [],
\"message\": \"Unrecognized key(s) in object: 'speech'\"
}
]",
"name": "ZodError",
"stack": "ZodError: [
{
\"code\": \"unrecognized_keys\",
\"keys\": [
\"speech\"
],
\"path\": [],
\"message\": \"Unrecognized key(s) in object: 'speech'\"
}
]
at get error [as error] (/app/node_modules/zod/lib/types.js:43:31)
at loadCustomConfig (/app/api/server/services/Config/loadCustomConfig.js:64:13)
at AppService (/app/api/server/services/AppService.js:22:25)
at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
at async startServer (/app/api/server/index.js:36:3)"
} ScreenshotsNo response Code of Conduct
|
Beta Was this translation helpful? Give feedback.
Replies: 2 comments
-
It's recognized on my end, from my startup logs: },
"speech": {
"tts": {
"openai": {
"voices": [
"alloy",
"echo",
"fable",
"onyx",
"nova",
"shimmer"
],
"apiKey": "${OPENAI_API_KEY}",
"model": "tts-1"
}
},
"stt": {
"openai": {
"apiKey": "${OPENAI_API_KEY}",
"model": "whisper-1"
}
}
}
} Are you using an older version of LibreChat? |
Beta Was this translation helpful? Give feedback.
-
@danny-avila I have purged docker and pulled from scratch, after which it started working. Thank you for looking into this! |
Beta Was this translation helpful? Give feedback.
It's recognized on my end, from my startup logs:
Are you using an older version of LibreChat?