Instructions to use Supertone/supertonic-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Supertonic
How to use Supertone/supertonic-3 with Supertonic:
from supertonic import TTS tts = TTS(auto_download=True) style = tts.get_voice_style(voice_name="M1") text = "The train delay was announced at 4:45 PM on Wed, Apr 3, 2024 due to track maintenance." wav, duration = tts.synthesize(text, voice_style=style) tts.save_audio(wav, "output.wav")
- Notebooks
- Google Colab
- Kaggle
Improve audio sample layout
Browse files
README.md
CHANGED
|
@@ -91,14 +91,59 @@ The open-weight package includes fixed preset voice styles for immediate local i
|
|
| 91 |
|
| 92 |
Here are a few reference/generated pairs from the audio sample demo:
|
| 93 |
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 102 |
|
| 103 |
## Performance Highlights
|
| 104 |
|
|
|
|
| 91 |
|
| 92 |
Here are a few reference/generated pairs from the audio sample demo:
|
| 93 |
|
| 94 |
+
**Call center, English**
|
| 95 |
+
Text: Good morning, thank you for calling. How can I help you today?
|
| 96 |
+
|
| 97 |
+
Reference voice
|
| 98 |
+
<audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/nora_reference.wav"></audio>
|
| 99 |
+
|
| 100 |
+
Supertonic 3 output
|
| 101 |
+
<audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/nora_supertonic3.wav"></audio>
|
| 102 |
+
|
| 103 |
+
**Character voice, Japanese**
|
| 104 |
+
Text: ใตใตใฃใ้ๅฑใใฆใใจใใใชใฎใใกใใใฉใใ้ใณ็ธๆใ่ฆใคใใใใโช
|
| 105 |
+
|
| 106 |
+
Reference voice
|
| 107 |
+
<audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/moka_reference.wav"></audio>
|
| 108 |
+
|
| 109 |
+
Supertonic 3 output
|
| 110 |
+
<audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/moka_supertonic3.wav"></audio>
|
| 111 |
+
|
| 112 |
+
**Elder character voice, Korean**
|
| 113 |
+
Text: ํผ์ ๋ ๋๊ธฐ์ ๊ธธ์ด ํํ๊ตฌ๋. ์ด ๋ก์ ๊ฒ์ ๊ฐ์ ธ๊ฐ๊ฑฐ๋ผ. ์ธ์ ๊ฐ ์ด๋ ์ด ๋ค ์ด๋ฆ์ ๋ถ๋ฅด๋๋ผ๋, ๋ถ๋ ๋น์ ์์ง ๋ง๊ฑฐ๋ผ.
|
| 114 |
+
|
| 115 |
+
Reference voice
|
| 116 |
+
<audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/alphonse_reference.wav"></audio>
|
| 117 |
+
|
| 118 |
+
Supertonic 3 output
|
| 119 |
+
<audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/alphonse_supertonic3.wav"></audio>
|
| 120 |
+
|
| 121 |
+
**Audiobook, English**
|
| 122 |
+
Text: I was not afraid of silence. I had lived with it long enough to know that, sometimes, it speaks more honestly than people do.
|
| 123 |
+
|
| 124 |
+
Reference voice
|
| 125 |
+
<audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/luna_reference.wav"></audio>
|
| 126 |
+
|
| 127 |
+
Supertonic 3 output
|
| 128 |
+
<audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/luna_supertonic3.wav"></audio>
|
| 129 |
+
|
| 130 |
+
**Audiobook, Japanese**
|
| 131 |
+
Text: ใใฎๆใใญใณใใณใฎ้งใฏใใคใซใชใไฝใๅใใใใฆใใใ็งใฏใใ ใฎ่จชๅ่
ใ ใจๆใฃใฆใใใใใใผใ ใบใฎ็ฎใฏใใงใซๅฅใฎ็ต่ซใซใใฉใ็ใใฆใใใ
|
| 132 |
+
|
| 133 |
+
Reference voice
|
| 134 |
+
<audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/watson_reference.wav"></audio>
|
| 135 |
+
|
| 136 |
+
Supertonic 3 output
|
| 137 |
+
<audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/watson_supertonic3.wav"></audio>
|
| 138 |
+
|
| 139 |
+
**News, English**
|
| 140 |
+
Text: Hereโs a story worth paying attention to. Supertone has released Supertonic 3, its on-device TTS model. This version expands support to thirty-one languages and improves reading stability.
|
| 141 |
+
|
| 142 |
+
Reference voice
|
| 143 |
+
<audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/keld_reference.wav"></audio>
|
| 144 |
+
|
| 145 |
+
Supertonic 3 output
|
| 146 |
+
<audio controls preload="metadata" src="https://huggingface.co/Supertone/supertonic-3/resolve/main/audio_samples/keld_supertonic3.wav"></audio>
|
| 147 |
|
| 148 |
## Performance Highlights
|
| 149 |
|