Transcript doesn't match LLM inputs/outputs
# support
g
and it's sometimes totally unusable in french. For example (call id: 4d88522c-65a3-4f0d-84bf-7787a90b9799): First message of my assistant : "Bonjour, je suis l'IA de Lonestone" In the transcript : "Bonjour, je suis Lia de Launcetown. Bonjour, je suis Lia de Lone Stone" Vapi has the exact input, so it should be the same in the transcript.
v
Hi @Godefroy @Lonestone, I'm an AI assistant for Vapi. I'll analyze available sources and get back to you shortly.
----------------------------- **While I generate an answer, here are some sources that might be helpful**: * [Core Models]() * [Web Calling]() * [Orchestration Models]() * [Update Assistant]() -----------------------------
### Answer It seems like you are experiencing issues with the accuracy of the transcription in French. This discrepancy can arise due to several factors including accents, speech clarity, or background noise which might affect the transcription model's performance [(1)]() . Vapi uses advanced models for transcribing speech, but like all automated systems, it may not always perfectly capture or interpret spoken language, especially when dealing with homophones or similar-sounding phrases in different dialects or languages. If the transcription errors are significantly impacting the usability, you might consider providing feedback directly on the specific instances where the discrepancies occur. This can help improve the model's accuracy over time. For now, ensuring clear, slow, and distinct pronunciation during calls can sometimes help mitigate these issues. For further details on how Vapi handles speech-to-text and other operations, you can refer to the official documentation on [Orchestration Models]() [(2)]() .
Got it. Tagging @User for additional help.
s
Use Deepgram's French model. It will fix your issue. Also, check out this video tutorial:

https://www.youtube.com/watch?v=AH5oS2w3EcQ

g
@Sahil Why would the first message be processed by the STT? (same for any other message from the AI) Btw Whisper is better than Deepgram in French.
@Sahil Hey! You said to ping you if needed 😄
s
Assistant messages aren't processed via transcriber. If you check the call logs and then search for "Transcript Output," you will notice that only users' messages are transcribed, not the assistant's response.
g
Ok so why is the transcript wrong?
s
Let's do one. Let's hop on a meeting and let's debug it during that process. Does that sound good to you?
g
Sure, I can be available tomorrow
s
Sent you appointment link.
g
What's your timezone? I'm available between 10am and 6pm in France (CEST / UTC+2)
Just saw the calendly in PM, thanks!
s
Sounds, good
j
@Sahil is this still true? i see the agent transcription happening but it's typically wrong, which then gets fed back in as model input causing errors
c
Yes, it is and you can use the modelOutput if you don't want it to be transcribed.
a
@Sahil this is happening to me too; Already try to put modelOutputInMessagesEnabled set to true too; but from the logs in VAPI i can see that OpenAI (Azure in my case) is getting the transcription from the TTS
c
can you create a new ticket? + add the call_id.
a
@Sahil already in support
4 Views