VoiceWizardPro
The VoiceWizardPro API allows you to access Microsoft Azure, Amazon Polly, Google Cloud, and IBM Watson voices without the need to create and manage multiple accounts. By choosing a tier and becoming a member on https://ko-fi.com/ttsvoicewizard/tiers, you will receive an allotted amount of TTS and Translation characters that refresh monthly.
Speech-to-Text or speech recognition with DeepGram has recently been added to Pro.
Here is the break down of the tiers available at https://ko-fi.com/ttsvoicewizard/tiers
| Tier | Price Per Month | TTS Characters Per Month | Translation Character Per Month | Speech Recognition Hours (DeepGram) | Rate Limiting |
|---|---|---|---|---|---|
| Acolyte | $3 | 100,000 | 50,000 | 1 | moderate |
| Magician | $5 | 250,000 | 50,000 | 3 | moderate |
| Enchanter | $6 | 0 | 500,000 | 3 | moderate |
| Witch | $10 | 500,000 | 100,000 | 5 | moderate |
| Sorcerer | $15 | 500,000 | 500,000 | 10 | moderate |
| Warlock | $18 | 1,000,000 | 100,000 | 10 | low |
| Wizard | $20 | 750,000 | 500,000 | 15 | low |
| Archmage | $50 | 2,000,000 | 1,000,000 | 25 | low |
| Deity | $100 | 4,000,000 | 2,000,000 | 50 | low |
I have permanently "discounted" using Amazon Polly and Google voices with pro. Basically your TTS Characters used is about 1/3 as much. So if you typed a 3 letter word you would only increase your usage by 1. (It's rounded so 4 letter word = 1 usage, 5 letter word = 2 usage)
Azure voices are still 1 to 1.
So you could use about 3 times as many characters if you are using Amazon Polly or Google for TTS.
All Tiers now have some translation characters
DeepGram Speech Recognition added to Pro (pre-release)
- Become Member on the Kofi: https://ko-fi.com/ttsvoicewizard/tiers
- Link your Discord to Kofi and join the Discord Server
- If you did not receive your discord role automatically please check out this article on collecting discord benefits
- Navigate to the
#get-api-key-betachannel in Discord- To get a key for the first time type:
/create-key - To refresh your key type:
/refresh-key
- To get a key for the first time type:
- Your key will be DM'ed to you by the Official TTS Voice Wizard Bot in Discord
- In TTS Voice Wizard navigate to Speech Provider > VoiceWizard Pro
-
Make sure "Use Voice Wizard Pro Key" is enabled and copy and paste your key from the discord DM to the "Voice Wizard Pro Key" text field
-
You can now choose whether to use the Pro Key for Azure, Amazon Polly and Translations. (It will automatically be used for Google Cloud voices since those are VoiceWizardPro Only)
- You can select the voice you wish to use from the "Text to Speech" Tab under "Voice Customization Options:
- Select Deepgram (Pro Only) from Settings > Audio
- Go to the Speech Provider > Voice Wizard Pro and scroll down to DeepGram Recogntion.
- Click you're speech to text hotkey (Ctrl + G) by default to activate speech recognition while in this tab.
- Monitor The dial
- If the needle seems to ignore your voice then your environment is really quiet and you need to more the slider to the left towards silent.
- If needle seems to think you're talking when you aren't you have a loud environment and you need to move the slider to the right towards loud.
- Minimum Audio Duration is the shortest duration a audio clip can have in seconds
- Maximum audio duration is the longest duration an audio clip can have with a soft cap of 25 seconds and a hard cap in the API of 30 seconds.
Leave me a Github Star ⭐ (it's free) or
