# 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:** 1

<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:** [March 15, 2023, 10:52am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/1 "2023-03-15T10:52:13Z")

</div>

Hi everyone, I want our users to record voice notes within GlideApps for e.g. hands-free documentation and transcribe this into fine tuned and summarized notes afterwards. Any experiences with this? A simple audio recording option Glide would be fine I guess, the rest can be zapped together. Thanks 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:** [March 16, 2023, 12:58am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/2 "2023-03-16T00:58:03Z")

</div>

> [@Sebastian\_Daus](#):
>
> A simple audio recording option Glide would be fine I guess

Unfortunately this is not possible as of now.

I imagine the flow would be:

- Record audio with an app on your device
- Upload that audio to Glide
- With a button, send that audio to Whisper API and get the transcription
- Use ChatGPT API to summarize that and get the text back to Glide using Glide API

---

<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:** [March 16, 2023, 1:49am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/3 "2023-03-16T01:49:01Z")

</div>

Exactly, that would be the idea 🙂

---

<div class="post-metadata">

**Author:** ![Jason](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/jason/32/14_2.png) [@Jason](https://community.glideapps.com/u/Jason)\
**Post date:** [April 5, 2023, 8:19pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/4 "2023-04-05T20:19:22Z")

</div>

![image](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/d/5/d5dd2c77ed34c3d6be6a4e3ba12ee68b21318201.png)

Ahem

---

<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 5, 2023, 8:39pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/5 "2023-04-05T20:39:08Z")

</div>

True - update came after the question I believe but I had difficulties making it work since it connects to the google cloud api. Did you?

---

<div class="post-metadata">

**Author:** ![Jason](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/jason/32/14_2.png) [@Jason](https://community.glideapps.com/u/Jason)\
**Post date:** [April 5, 2023, 8:40pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/6 "2023-04-05T20:40:18Z")

</div>

We’re unfortunately still waiting for Google to finalize the OAuth flow verification. Shouldn’t be much longer… We have to have it live in production to submit for verification, but nobody can use it unless its verified. Classic.

---

<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 5, 2023, 8:40pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/7 "2023-04-05T20:40:42Z")

</div>

Thanks!

---

<div class="post-metadata">

**Author:** ![Evgeny\_B](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/evgeny_b/32/57101_2.png) [@Evgeny\_B](https://community.glideapps.com/u/Evgeny_B)\
**Post date:** [April 5, 2023, 8:57pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/8 "2023-04-05T20:57:10Z")

</div>

Wanna build it together? I have this very functionality already built for an iOS shortcut (built it for myself). I’m using OpenAI’s Whisper to transcribe audio though. Adapting it for Glide would be awesome 🙂

---

<div class="post-metadata">

**Author:** ![Jeremy](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/jeremy/32/29121_2.png) [@Jeremy](https://community.glideapps.com/u/Jeremy)\
**Post date:** [April 7, 2023, 6:14pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/9 "2023-04-07T18:14:12Z")

</div>

Should be working now - we’re verified as of today. Also we added OpenAI’s whisper speech to text engine 😄 both work well. I prefer whisper’s output. Show us what you build!

---

<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 7, 2023, 10:00pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/10 "2023-04-07T22:00:02Z")

</div>

It works! Goosebumps 😃

---

<div class="post-metadata">

**Author:** ![Tim\_Gestels](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/tim_gestels/32/44044_2.png) [@Tim\_Gestels](https://community.glideapps.com/u/Tim_Gestels)\
**Post date:** [April 8, 2023, 11:24am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/11 "2023-04-08T11:24:39Z")

</div>

Very cool 🙂

It’s working for me using Whisper, however I couldn’t get the google version work.  
According to some reviews I read it would be even a little bit better.  
I’m getting this error message, probably I’ve don something wrong with the setup?

 ![image](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/2/c/2c50561b77cebe71e2d62ec9587cd1403c67c258.png)

It’s using the same audio file that is working with the openai integration.

---

<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 13, 2023, 1:26pm UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/12 "2023-04-13T13:26:47Z")

</div>

Hi Community and @Tim_Gestels

Trying to use OpeanAI Speech to text and receiving this error message:

Speech to text: Error 400: Bad Request - { “error”: { “message”: “Invalid file format. Supported formats: [‘m4a’, ‘mp3’, ‘webm’, ‘mp4’, ‘mpga’, ‘wav’, ‘mpeg’]”, “type”: “invalid\_request\_error”, “param”: null, “code”: null } }

Does anyone know how to help me?

Error message image

 ![IMG_5080.HEIC](https://us1.discourse-cdn.com/flex002/uploads/glideapps/original/3X/1/2/12630926e83b5f349f48d6ecebd9b1e3fca0eb0e.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:** [April 14, 2023, 12:12am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/13 "2023-04-14T00:12:19Z")

</div>

Do you know what file extension were you using for your upload? What type of device are you trying this on?

---

<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, 12:44am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/14 "2023-04-14T00:44:07Z")

</div>

Hi @ThinhDinh ,

mp4, according to the URL generated by the Audio Recorder from Glide. I also downloaded the file to double check and it was working fine, I mean, it was a mp4 file indeed. I was using Glide app to run/simulate the Actions.

---

<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:** [April 14, 2023, 2:03am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/15 "2023-04-14T02:03:10Z")

</div>

Which OS were you trialling it on: iOS/MacOS/Android/Windows?

---

<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, 4:05am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/16 "2023-04-14T04:05:12Z")

</div>

The Whisper API is still in beta, and it fails on mp4 files created by Safari. Users have reported this on the OpenAI forums.

---

<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, 4:06am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/17 "2023-04-14T04:06:43Z")

</div>



---

<div class="post-metadata">

**Author:** ![Simon\_Hill](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/simon_hill/32/94730_2.png) [@Simon\_Hill](https://community.glideapps.com/u/Simon_Hill)\
**Post date:** [April 14, 2023, 4:37am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/18 "2023-04-14T04:37:17Z")

</div>

This is fantastic. Another great leap for Glide.

Stepping back, I celebrate Glide’s new found revenue driver, which is to leverage users clamor to integrate external services. I really hope this helps minimize the cost for apps that are designed to be integration-free.

---

<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, 10:46am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/19 "2023-04-14T10:46:22Z")

</div>

Hi @ThinhDinh,

MacOS/Safari.

I Think @david nailed. I will try to use Chrome. Hope it works.

All the best and thank you all the for the help!

Edu

---

<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 14, 2023, 11:20am UTC](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184/20 "2023-04-14T11:20:04Z")

</div>

@Sebastian_Daus have you compared how Whsiper performs in comparison to iOS or Androids dictation function?

[Next page](https://community.glideapps.com/t/voice-notes-speech-to-text-chatgpt/59184.md?page=2)
