Voice Selection
TTS Buddy offers 300+ voices with 30+ language modes. Kokoro voices provide native language options, and Supertonic voices can be used across supported languages such as French, German, Korean, Japanese, Arabic, Spanish, and more. See Language Support for the complete language list and provider codes.
Browsing Voices
On the dashboard, click the Voice dropdown to see all available options. Voices are organized by language. When both providers support a language, they appear together in the same group. For example, French includes Kokoro's Camille voice plus Supertonic Fast voices such as Louis, Hugo, Léa, and Chloé.
Each voice shows:
- Name — The voice's display name
- Tier — Fast, Premium, Standard, or Basic
- Gender — Male or female
- Preview button — Hear a short sample before committing
Provider Families
Supertonic Fast Voices
Supertonic voices are shown under each supported language instead of a generic "Multilingual" group. They use native display names for each language while keeping stable API voice IDs. For example, choosing Louis under French sends voice: "st_m1" with lang_code: "fr", while choosing Noah under German sends voice: "st_m1" with lang_code: "de".
Supertonic Fast currently appears in these public language modes: American English, Arabic, Bulgarian, Croatian, Czech, Danish, Dutch, Estonian, Finnish, French, German, Greek, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Latvian, Lithuanian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Turkish, Ukrainian, and Vietnamese.
| API voice ID | Example English name | Example French name | Gender | Tier |
|---|---|---|---|---|
| st_m1 | Liam | Louis | Male | Fast |
| st_m2 | Noah | Hugo | Male | Fast |
| st_m3 | Ethan | Jules | Male | Fast |
| st_m4 | James | Lucas | Male | Fast |
| st_m5 | Lucas | Gabriel | Male | Fast |
| st_f1 | Ava | Camille | Female | Fast |
| st_f2 | Emma | Léa | Female | Fast |
| st_f3 | Mia | Chloé | Female | Fast |
| st_f4 | Grace | Manon | Female | Fast |
| st_f5 | Lily | Inès | Female | Fast |
Kokoro Native Voices
Kokoro voices appear under their native language groups:
| Language | Voices |
|---|---|
| American English | Madison, Sophia, Zoe, Allie, Aria, Cora, Harper, Nova, Skye, Jessica, Riley, Michael, Felix, Parker, Nathan, Mason, Logan, Oscar, Samuel, Jackson |
| British English | Emma, Isabella, Alice, Lily, George, Felix, Lewis, Daniel |
| Spanish | Valentina, Alejandro, Diego |
| French | Camille |
| Hindi | Priya, Ananya, Arjun, Vikram |
| Italian | Giulia, Marco |
| Japanese | Yuki, Sakura, Akiko, Mayumi, Hiroshi |
| Portuguese | Isabela, Rafael, Gabriel |
| Chinese | Mei, Li, Xin, Wen, Wei, Jun, Lei, Chen |
Voice Tiers
| Tier | Description |
|---|---|
| Fast | Supertonic voices optimized for quick generation across many languages. |
| Premium | Highest-quality Kokoro voices with natural intonation and expression. |
| Standard | High-quality Kokoro voices suitable for everyday use. |
| Basic | Functional Kokoro voices for straightforward text conversion. |
Speed Options
Each voice supports five speed settings:
| Speed | Label | Best For |
|---|---|---|
| 0.5x | Very Slow | Language learning, careful study |
| 0.8x | Slow | Detailed comprehension, note-taking |
| 1.0x | Normal | Natural speaking pace |
| 1.2x | Fast | Quick review, familiar material |
| 1.5x | Very Fast | Speed review, scanning content |
Choosing The Right Voice
For Studying
Pick a clear, steady voice at Normal or Slow speed. Voices with natural pauses work well for absorbing complex material.
For Long-Form Listening
Choose a warm, conversational voice like Madison or Sophia. You'll be listening for a while, so comfort matters.
For Professional Content
Select a clear, authoritative voice that matches the tone of your material.
For Language Learning
Choose a voice in the language you're learning. Use Slow (0.8x) or Very Slow (0.5x) speeds to help with pronunciation.
For Quick Conversions
Use Fast Supertonic voices for the quickest generation times.
Persistent Preferences
TTS Buddy remembers your voice, language, and speed settings between sessions. When you return to the dashboard, your last-used settings are automatically applied.
You can set different voices for the Text-to-Speech page and the Chrome Extension (Web Buddy). Configure your Web Buddy voice in Settings.