Speech to Text: Transcribe service not working properly (used Deepgram's Nova 3) **Text to Speech**: It is sometimes missing to produce parts of voice and also the numbers coming is the text response is not properly hanled while converting it to speech

Add 0.5–1 sec of silence at the start of audio before using Deepgram Nova-3 for better transcription, and for vapi TTS, switch to the Aura-2 voice, format numbers using SSML, and add slight playback delays to avoid speech cutoffs..

And any idea as why is this happening with model set to sonar-pro in perplexity. It is abruptly stopping https://cdn.discordapp.com/attachments/1393110477726289960/1393162775160688700/Screenshot_2025-07-11_at_3.00.17_PM.png?ex=68722b71&is=6870d9f1&hm=77b0f17b26a0ab5d4fe67d58e4af8933b711f8bb8f4d454b526e89bc1c38da7f&

Hey Ska, Thank you for reaching out. Please note that our team does not operate over the weekend. We'll be back in the office on Monday and will dive straight into your issue then to determine the best way forward.

We truly apologize for the inconvenience you’ve faced. To help you resolve this issue quickly, please share your call_id with us. Thank you for your understanding..

Hi @Kings_big💫 I have sent you the chat id in your dm

Marketing this ticket as solved ✅

Not yet solved @Kings_big💫

Thank you for sharing your information! I’ll keep you posted as I work on resolving your issue. Your patience is truly appreciated..

Any update here @Kings_big💫 ?

Hey, could you please share a few more chat IDs? We looked into the shared chat IDs, but we are unable to reproduce this. Sharing a few more chat IDs will help us reproduce this and eventually get it fixed for you..

Shared with you in your DM

Seen looking into it

The error can be reproduced by selecting perplexity in the provider

Hey, thanks for sharing the chat_ids. I've forwarded this to the executives, and I'll get back to you once I receive the response from them..

We are trying to launch some things on prod soon with mjor portion of our backend dependent on VAPI, hence would appreciate if this could be solved soon.

Hey Ska, I sincerely apologize for the delay in our responses this week. We experimented with some process adjustments that didn’t work as intended, and unfortunately, this caused some disruptions. That’s entirely my responsibility. Just a quick note—our team is unavailable on weekends. However, if something urgent or critical comes up, feel free to reach out to me directly, and I’ll assist you. The support issues will be resolved in the coming weeks, and starting Monday, you can expect more consistent and improved support. Thank you so much for your patience and for continuing to stick with us!

Any update on this @Shubham Bajaj and @Kings_big💫 ?

Hi @Ska , We've confirmed there's might be an issue that's causing responses to cut off mid-generation. Switch to OpenAI GPT-4o for production. This will resolve the truncation issues immediately. Let's connect in DMs to reproduce the issue and schedule a call to discuss how we can fix this. For now, the immediate solution is switching to another model. Don't delay your launch - OpenAI models will give you reliable performance without these issues. Thanks for the chat_Ids that helped us identify this.

@Kings_big💫 I am aware that with other models this abrupt behaviour is not observed. But it won't be solving my issue.

Hi, First off, we want to sincerely apologize for the delay in getting back to you. We understand how frustrating it is to wait - especially when you're counting on us - and we owe you a clear explanation of what’s been happening and how we’re addressing it. Over the past few weeks, we've seen a significant increase in support requests. While this reflects exciting growth, it has also stretched our small team and exposed some real challenges in scaling our support operations. To improve your experience, we’ve taken a step back to reassess our approach. Here’s what we’re implementing: - Smarter Support Through Automation: We’re investing in our AI support systems to help you resolve issues more efficiently. Soon, our support bot will offer expanded capabilities, making it easier to access accurate, instant help—particularly for common or repetitive queries. - Expanding the Support Team: To meet growing demand, we’re adding 2–3 new team members focused on managing support volume and improving response times. - Prioritized SLAs for High-Usage Accounts: We’re introducing service level improvements for users who are growing with us: - Accounts with usage over 1,000 minutes/month will receive prioritized support. - For all general inquiries, we’re establishing a standardized 48-hour response time. We’re confident these steps will lead to faster, more reliable support and help us better serve you as you grow with us. Also, in case you still need help with this ongoing ticket, do let us know, and we will help you get this resolved as soon as possible. Thank you for your continued patience and for being part of our journey. Warm regards, Vapi Team