Originally created by @khalilxg on GitHub (Jan 2, 2025).
so im using latest open-webui web version,
im using openai apis;
so when i click on call or voice-record to interact using voice, i got this error in the frontend "400: This model requires that either input content or output modality contain audio."
when clicking also on call it throws this error too "404: This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?"
Originally created by @khalilxg on GitHub (Jan 2, 2025).
so im using latest open-webui web version,
im using openai apis;
so when i click on call or voice-record to interact using voice, i got this error in the frontend "400: This model requires that either input content or output modality contain audio."
when clicking also on call it throws this error too "404: This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?"
thanks, how about forcing stt to be in certain language, exemple im talking russian i want it to return in russian language not latin :/ docs are in russian language
@khalilxg commented on GitHub (Jan 2, 2025):
thanks, how about forcing stt to be in certain language, exemple im talking russian i want it to return in russian language not latin :/ docs are in russian language
i havc the same issue. will this be fixed? not using chatgpt but when calling, there is an error with the speech, but when i press the read outloud button, there isnt an error: {detail: "400: property 'chat_id' is unsupported, did you mean 'seed'?"}
@Blygf commented on GitHub (Jan 3, 2025):
i havc the same issue. will this be fixed? not using chatgpt but when calling, there is an error with the speech, but when i press the read outloud button, there isnt an error: {detail: "400: property 'chat_id' is unsupported, did you mean 'seed'?"}
i havc the same issue. will this be fixed? not using chatgpt but when calling, there is an error with the speech, but when i press the read outloud button, there isnt an error: {detail: "400: property 'chat_id' is unsupported, did you mean 'seed'?"}
BEST solution is to wait or create omni models support, whisper models are not a fiable solution
@khalilxg commented on GitHub (Jan 3, 2025):
> i havc the same issue. will this be fixed? not using chatgpt but when calling, there is an error with the speech, but when i press the read outloud button, there isnt an error: {detail: "400: property 'chat_id' is unsupported, did you mean 'seed'?"}
BEST solution is to wait or create omni models support, whisper models are not a fiable solution
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @khalilxg on GitHub (Jan 2, 2025).
so im using latest open-webui web version,
im using openai apis;
so when i click on call or voice-record to interact using voice, i got this error in the frontend "400: This model requires that either input content or output modality contain audio."
when clicking also on call it throws this error too "404: This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?"
@tjbck commented on GitHub (Jan 2, 2025):
Omnimodels are not supported currently.@khalilxg commented on GitHub (Jan 2, 2025):
thanks, how about forcing stt to be in certain language, exemple im talking russian i want it to return in russian language not latin :/ docs are in russian language
@khalilxg commented on GitHub (Jan 2, 2025):
all models are returning in latin alphabets now
@khalilxg commented on GitHub (Jan 2, 2025):
im using whisper api and whisper local, both have same output
@Blygf commented on GitHub (Jan 3, 2025):
i havc the same issue. will this be fixed? not using chatgpt but when calling, there is an error with the speech, but when i press the read outloud button, there isnt an error: {detail: "400: property 'chat_id' is unsupported, did you mean 'seed'?"}
@khalilxg commented on GitHub (Jan 3, 2025):
BEST solution is to wait or create omni models support, whisper models are not a fiable solution