VoiceWizardPro
Subscribe to Ko-Fi or Patreon and experience a world of powerful features that will transform your TTS and translation experience:
-
✨ Instant Access to Premium Voices: Enjoy hundreds of voices from leading cloud services, including:
- Microsoft Azure
- Amazon Polly
- Google Cloud
- IBM Watson
-
🌍 Multilingual Magic: Translate your voices into 70+ supported languages, talk to your friends from all over the world
-
🎤 Crystal-Clear Transcriptions: Gain access to speech recognition through DeepGram's Nova-2 model, the fastest and most accurate speech-to-text API.
Your subscription not only enhances your capabilities but also supports future development:
- 💪 Empower Ongoing Development: Your contribution assists in server upkeep, covers character costs from premium APIs, and fuels future software innovations.
Ready to elevate your TTS game? Dive into VoiceWizardPro now! For detailed insights, explore our VoiceWizardPro GitHub Wiki page.
Unlock the power of VoiceWizardPro today! 🚀
| 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 (and IBM Watson) 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)
- Support added for TTS Voices from IBM Watson
- Support added for for 40 new languages
- Tiers above Acolyte now have 1000 max characters per request (Acolyte still has 300 per request)
- Deepgram now using their nova 2 model (English only)
- 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 Recognition.
- 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
