# Voice Notes & Speech to Text + ChatGPT

**URL:** <https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184>\
**Category:** Ask for Help\
**Created:** [March 15, 2023, 10:52am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184 "2023-03-15T10:52:13Z")\
**Posts on this page:** 20\
**Page:** 2

<div class="post-metadata">

**Author:** ![edumaga](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/edumaga/32/57518_2.png) [@edumaga](https://community.glideapps.com/u/edumaga)\
**Post date:** [April 14, 2023, 11:47am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/21 "2023-04-14T11:47:32Z")

</div>

Hi @david ,

It is working with Chrome on my MacAir.

When I tried with my iPhone8 it did not (even with Chrome Browser). Have a clue?

All the best,  
Edu

---

<div class="post-metadata">

**Author:** ![david](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/david/32/62831_2.png) [@david](https://community.glideapps.com/u/david)\
**Post date:** [April 14, 2023, 2:16pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/22 "2023-04-14T14:16:45Z")

</div>

On iOS, all browsers are actually Safari under the hood.

---

<div class="post-metadata">

**Author:** ![RISHTACORNER](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/rishtacorner/32/56211_2.png) [@RISHTACORNER](https://community.glideapps.com/u/RISHTACORNER)\
**Post date:** [April 14, 2023, 2:35pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/23 "2023-04-14T14:35:16Z")

</div>

Absolutely frigging amazing!!! Excuse the casual nature of my comment but am really impressed and excited about using this feature and the new possibilities it brings

---

<div class="post-metadata">

**Author:** ![Sebastian\_Daus](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/sebastian_daus/32/54381_2.png) [@Sebastian\_Daus](https://community.glideapps.com/u/Sebastian_Daus)\
**Post date:** [April 14, 2023, 6:23pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/24 "2023-04-14T18:23:29Z")

</div>

Not yet - fully testing all other cases next week. What do you think is the reason for the performance gap?

---

<div class="post-metadata">

**Author:** ![Gregory](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/gregory/32/21180_2.png) [@Gregory](https://community.glideapps.com/u/Gregory)\
**Post date:** [April 15, 2023, 7:04am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/25 "2023-04-15T07:04:59Z")

</div>

Thanks!  
I don’t know whether there is a performance gap.

---

<div class="post-metadata">

**Author:** ![Biotech\_Sol](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/biotech_sol/32/58480_2.png) [@Biotech\_Sol](https://community.glideapps.com/u/Biotech_Sol)\
**Post date:** [May 11, 2023, 3:18am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/26 "2023-05-11T03:18:25Z")

</div>

We’re thrilled with the Whisper integration and believe it has great potential for building new tools. However, we’ve run into an issue. Despite recording audio of various lengths, only one second of it is being utilized. When we check the ‘Usage’ tab on the Open AI website, all Whisper requests are also logged as one-second long.

We’re unsure if this is due to a limitation in audio processing on your end or if it’s a bug with Open AI’s Whisper. Could you please help us identify and resolve this problem?

---

<div class="post-metadata">

**Author:** ![Trustin](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/trustin/32/88217_2.png) [@Trustin](https://community.glideapps.com/u/Trustin)\
**Post date:** [May 12, 2023, 3:06pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/27 "2023-05-12T15:06:59Z")

</div>

Hi, did you generate the speech to text within the data column or on action trigger? Also will you be able to provide a snapshot of your data ?

---

<div class="post-metadata">

**Author:** ![Biotech\_Sol](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/biotech_sol/32/58480_2.png) [@Biotech\_Sol](https://community.glideapps.com/u/Biotech_Sol)\
**Post date:** [May 13, 2023, 1:12pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/28 "2023-05-13T13:12:12Z")

</div>

Yes, I generate it exactly within data.

 ![Screen Shot 2023-05-13 at 10.11.41 AM](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/6/1/6184cfaa0dfdd46625a5fcdc31709198b45c25be.jpeg)

---

<div class="post-metadata">

**Author:** ![ThinhDinh](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/thinhdinh/32/49_2.png) [@ThinhDinh](https://community.glideapps.com/u/ThinhDinh)\
**Post date:** [May 13, 2023, 11:31pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/29 "2023-05-13T23:31:27Z")

</div>

What if you use it as an action instead of a column?

---

<div class="post-metadata">

**Author:** ![Biotech\_Sol](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/biotech_sol/32/58480_2.png) [@Biotech\_Sol](https://community.glideapps.com/u/Biotech_Sol)\
**Post date:** [May 14, 2023, 9:10pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/30 "2023-05-14T21:10:09Z")

</div>

The same

---

<div class="post-metadata">

**Author:** ![ThinhDinh](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/thinhdinh/32/49_2.png) [@ThinhDinh](https://community.glideapps.com/u/ThinhDinh)\
**Post date:** [May 14, 2023, 11:42pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/31 "2023-05-14T23:42:09Z")

</div>

![image](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/b/a/baa98b211a5dede28fc7d1e3f92b22c88a9d8dad.png)

I can’t reproduce it. I uploaded a 3:22 video of a person speaking words, and it does work for longer than 1 second.

---

<div class="post-metadata">

**Author:** ![Sebastian\_Daus](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/sebastian_daus/32/54381_2.png) [@Sebastian\_Daus](https://community.glideapps.com/u/Sebastian_Daus)\
**Post date:** [May 16, 2023, 8:34am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/32 "2023-05-16T08:34:56Z")

</div>

I ran into a similar issue and realized that files are translated but not inputs from the glide voice recorder. There is a difference in the file format m4a & mp4 but both work according to OpenAI. However, if you open them from the data table, the glide recorder version is opened as a link and then downloaded so it might be a storage issue. Found this in the OpenAI FAQ which might be the answer:

**Can I send links to audio files instead?**  
We don’t support this right now. You’ll need to send a file in one of the formats listed above.

See: [Whisper API FAQ | OpenAI Help Center](https://help.openai.com/en/articles/7031512-whisper-api-faq)

@ThinhDinh @Biotech_Sol

---

<div class="post-metadata">

**Author:** ![nixkulinax](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/nixkulinax/32/73708_2.png) [@nixkulinax](https://community.glideapps.com/u/nixkulinax)\
**Post date:** [May 16, 2023, 6:25pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/33 "2023-05-16T18:25:30Z")

</div>

Have you tried not to upload the file, but to record it directly in the application? As on the example of David

---

<div class="post-metadata">

**Author:** ![ThinhDinh](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/thinhdinh/32/49_2.png) [@ThinhDinh](https://community.glideapps.com/u/ThinhDinh)\
**Post date:** [May 16, 2023, 11:18pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/34 "2023-05-16T23:18:19Z")

</div>

I recorded part of the same audeo and it still works for me.

 ![image](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/1/a/1a54f37a05fae2fbb1c306d379ec715f4cb47188.jpeg)

---

<div class="post-metadata">

**Author:** ![CDan](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/cdan/32/44535_2.png) [@CDan](https://community.glideapps.com/u/CDan)\
**Post date:** [July 28, 2023, 8:38am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/35 "2023-07-28T08:38:00Z")

</div>

@ThinhDinh Hi, I am not sure what I am doing wrong, but the speech to text is not working for me. I kindly ask that you help me look at the table I created below. Is there something I am supposed to do.

 ![Speech to Text Table](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/4/4/44d6b9d90c25598a3806c8b69e9dfd109e7bbc8a.jpeg)

Thanks for your help

---

<div class="post-metadata">

**Author:** ![CDan](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/cdan/32/44535_2.png) [@CDan](https://community.glideapps.com/u/CDan)\
**Post date:** [August 7, 2023, 8:11am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/36 "2023-08-07T08:11:42Z")

</div>

Any help please. I am still stuck. Is there anyone that can assist?

---

<div class="post-metadata">

**Author:** ![ThinhDinh](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/thinhdinh/32/49_2.png) [@ThinhDinh](https://community.glideapps.com/u/ThinhDinh)\
**Post date:** [August 7, 2023, 9:28am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/37 "2023-08-07T09:28:28Z")

</div>

What file extension are you seeing for your audio file?

---

<div class="post-metadata">

**Author:** ![CDan](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/cdan/32/44535_2.png) [@CDan](https://community.glideapps.com/u/CDan)\
**Post date:** [August 7, 2023, 9:40am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/38 "2023-08-07T09:40:41Z")

</div>

Many thanks @ThinhDinh.

It’s MP3. I used Glide recorder from Chrome browser.

Something like this:  
[https://storage.googleapis.com/glide-prod.appspot.com/uploads-v2/KgvnQ2ssAyJ1u23mZ72J/pub/0pYpCqYznAwetZ4MBf7A.mp3](https://storage.googleapis.com/glide-prod.appspot.com/uploads-v2/KgvnQ2ssAyJ1u23mZ72J/pub/0pYpCqYznAwetZ4MBf7A.mp3)

Thank you.

---

<div class="post-metadata">

**Author:** ![ThinhDinh](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/thinhdinh/32/49_2.png) [@ThinhDinh](https://community.glideapps.com/u/ThinhDinh)\
**Post date:** [August 7, 2023, 9:42am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/39 "2023-08-07T09:42:37Z")

</div>

I assume you have already connected your API key with the OpenAI integration, and you have a card tied to OpenAI?

---

<div class="post-metadata">

**Author:** ![CDan](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/cdan/32/44535_2.png) [@CDan](https://community.glideapps.com/u/CDan)\
**Post date:** [August 7, 2023, 9:44am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/40 "2023-08-07T09:44:37Z")

</div>

Yes. I copied the API key from ChatGPT and pasted in the integration, but I am not sure what ‘a card tied to OpenAI’ mean.

How can I go about doing that?

[Previous page](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184.md?page=1)

[Next page](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184.md?page=3)
