Made something similar which also uses Whisper to support voice memos (talk to GPT) and TTS (hear GPT’s responses)
Not sure it warrants a separate post, so sharing it here.
Also when i send something to the bot i can only send video, (with the iOS app) it makes more sense to send audio. Is this something you can change?
Finally, you should have a privacy policy for a service like this.
If you send /voices you can pick from multiple voices.
Right now it only shows voices in English, but you can send the secret `/setvoice <voiceName>` with an Amazon Polly[0] neural voice and it will work as well.
The only downside right now is that I don't auto-identify languages, so if you set it to Dutch, but ask a question in English, you'll get a response in English with a very Dutch accent haha.
P.S. And yes @aero-glide2 is correct that you can toggle between Telegram's audio/video inputs by tapping the camera/microphone icon. – Right now MarcBot only supports audio inputs.
[0] https://docs.aws.amazon.com/polly/latest/dg/voicelist.html
Currently considering either pre-recording all the outputs (ugh) or using the browser's TTS api (ugh^2) :)
If you speak other languages than English, make sure to give those a try well. It should understand you and respond in the same language.
Still, most people won't want to self-host it, so the business model might work, good luck!
I'm in a similar mood, but most of the indie maker's products are created this way and some end up scaling pretty well and turned in good investments, as they are usually cost-effective.
I'm very much the minority, as I like to self-host, but it seems to me that an OSS solution would do the same thing,and equally reliably.
Then again, the value proposition in this is that it's hosted and you don't have to deal with OpenAI keys, so that's what users are paying for.
There is a monthly subscription for 5USD which allows you to send up to 1000 messages every month. A yearly subscription costs 50USD.
Cool project!
I just finished something similar in Telegram, I added a way to connect to "live data" via system commands, so the bot can get weather updates or cryptocurrency prices. I want to wire it up to send emails, make reminders, view or update the calendar and see what else makes sense.
If you force the bot to decide to do something (eg: If you feel the user want to start again, respond with --RESTART--) I think you could make AI that feels sentient or can do things on its own.
A curious experiment for now, let's see how it goes:
Ideally there are no chat logs being kept at all and chat logs are only enabled temporarily for an individual user when debugging issues.
They don't provide their business address nor their country or phone number. How can it be trusted?
Privacy Policy: I DO NOT log/store anything from users chat (except the numeric telegram-id and the language preference). And I DO NOT send any user info to OpenAI as well (I would rather shut it down)
In case you don’t use Telegram, I made one for WhatsApp: http://wa.me/19893946588
