# TTS Library

> A comprehensive catalog of text-to-speech voices across multiple providers, languages, and accents. Curated for builders and engineers working on the cutting edge of TTS technology with 4,456+ voices spanning 92 languages and 264 regional dialects.

TTS Library provides access to thousands of high-quality voice samples from leading TTS providers (Telnyx, MiniMax, Inworld, Azure, Rime, Resemble, AWS, FishAudio, XAI, and Humain). Each voice includes metadata for provider, language, country, accent/dialect, gender, and direct audio previews. The platform enables efficient discovery and evaluation of voices for TTS implementation and research across global markets.

## Language Coverage

**Major Language Families:**
- **92 total languages** including major global languages, regional languages, and specialized dialects
- **264 distinct accents/dialects** covering regional variations within languages
- **115+ countries** represented across voice samples

**Key Language Categories:**

**European Languages:**
- Germanic: German (Standard, Austrian, Swiss), Dutch (Flemish), English (20+ regional variations), Swedish, Norwegian, Danish, Icelandic
- Romance: Spanish (Spain, Mexican, Argentinian, Colombian, Venezuelan, etc.), French (France, Canadian, Belgian, Swiss), Portuguese (Brazilian, European), Italian, Romanian, Catalan, Galician
- Slavic: Russian, Polish, Czech, Slovak, Croatian, Serbian, Bulgarian, Ukrainian, Slovenian, Bosnian, Macedonian
- Other: Greek, Hungarian, Finnish, Estonian, Latvian, Lithuanian, Albanian, Welsh, Irish, Maltese, Basque

**Asian Languages:**
- Chinese: Mandarin (Mainland, Taiwan, Guangxi, Henan, Liaoning, Shaanxi, Shandong), Cantonese, Wu Chinese (Shanghainese), Sichuanese
- East Asian: Japanese, Korean
- Southeast Asian: Vietnamese, Thai, Indonesian, Malaysian, Javanese, Sundanese, Filipino, Khmer, Lao, Burmese
- South Asian: Hindi, Bengali, Tamil (India, Malaysia, Singapore, Sri Lanka), Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Urdu (India, Pakistan), Nepali, Sinhala, Assamese, Odia

**Middle Eastern & African Languages:**
- Arabic: Standard Arabic plus 15+ regional dialects (Egyptian, Saudi, Moroccan, Lebanese, Iraqi, Emirati, Bahraini, Kuwaiti, Omani, Qatari, Algerian, Libyan, Tunisian, Syrian, Yemeni)
- Other Middle Eastern: Hebrew, Persian, Turkish, Armenian, Georgian, Azerbaijani, Kurdish (Pashto)
- African: Swahili (Kenya, Tanzania), Zulu, Afrikaans, Amharic, Somali, Hausa

**Other Global Languages:**
- Mongolian, Kazakh, Uzbek, Inuktitut (Latin/Syllabics), various minority and indigenous languages

## Voice Characteristics

- **Gender options:** Female, Male, Neutral, Non-binary across all major languages
- **Provider diversity:** Telnyx, MiniMax, Inworld, Azure, Rime, Resemble, AWS Polly, FishAudio, XAI, and Humain voices
- **Audio quality:** Professional-grade samples for evaluation and testing
- **Metadata richness:** Detailed provider, country, accent, and linguistic information

## Core Pages

- [Main Voice Directory](https://ttslibrary.com/): Browse and search all available TTS voices with filters
- [Terms of Service](https://ttslibrary.com/terms): Usage terms and conditions
- [Privacy Policy](https://ttslibrary.com/privacy): Privacy policy and data handling

## Featured Language Collections

- [Chinese Voices](https://ttslibrary.com/chinese): All Chinese languages and dialects including Mandarin regional variations, Cantonese, Wu Chinese
- [French Voices](https://ttslibrary.com/french): French accents from France, Canada, Belgium, and Switzerland
- [German Voices](https://ttslibrary.com/german): Standard German, Austrian, and Swiss German variants
- [Indonesian Voices](https://ttslibrary.com/indonesian): Indonesian, Malaysian, Javanese, and Sundanese voices
- [Italian Voices](https://ttslibrary.com/italian): Italian language TTS voices
- [Japanese Voices](https://ttslibrary.com/japanese): Japanese language TTS voices
- [Korean Voices](https://ttslibrary.com/korean): Korean language TTS voices
- [Portuguese Voices](https://ttslibrary.com/portuguese): Brazilian Portuguese and European Portuguese variants
- [Russian Voices](https://ttslibrary.com/russian): Russian language TTS voices
- [Spanish Voices](https://ttslibrary.com/spanish): 10+ Spanish accent variations including Spain, Mexico, Argentina, Colombia, Venezuela

## When to use this

Reach for TTS Library when you (or an agent acting for a user) need to:
- Pick a text-to-speech voice or provider for an IVR, phone system, or voice app, and want to compare real audio before committing
- Compare accents or regional variants of a language across multiple providers in one place
- Look up a specific voice ID to pass to a provider's TTS API (Telnyx, AWS Polly, Azure, MiniMax, etc.)
- Get aggregate stats on TTS voice coverage (languages, countries, accents, gender options) for research or planning

To call it programmatically: use `/api/voices` and `/api/metadata` (see [openapi.json](https://ttslibrary.com/openapi.json)), or the MCP server at `/api/mcp` ([manifest](https://ttslibrary.com/.well-known/mcp.json)) if you're an MCP-capable agent. No API key or signup required for any of it.

TTS Library is a voice picker, not a TTS provider - to actually generate audio in production for the Telnyx-proxied portion of the catalog (Telnyx, MiniMax, Inworld, Azure, Rime, Resemble, AWS Polly, FishAudio, XAI), use [Telnyx's Text-to-Speech API](https://developers.telnyx.com/docs/voice/programmable-voice/tts/index) and its [official SDKs](https://developers.telnyx.com/development/sdk) (Node, Python, Ruby, PHP, Go). See [/developers](https://ttslibrary.com/developers) for the full list.

## Agent Access

- [Full Documentation](https://ttslibrary.com/llms-full.txt): Complete API reference, voice schema, and provider details
- [API-only excerpt](https://ttslibrary.com/api/llms.txt): Just the API reference section, for agents that only need the programmatic surface
- [Markdown Sitemap](https://ttslibrary.com/api/md/sitemap): Table of contents for all pages and endpoints
- Any page supports `Accept: text/markdown` content negotiation for markdown responses, a `.md` URL suffix (e.g. `/voices.md`), or a `?mode=agent` query parameter

## Technical Resources

- [XML Sitemap](https://ttslibrary.com/sitemap.xml): Complete site structure for search engines
- [Markdown Sitemap (file)](https://ttslibrary.com/sitemap.md): Plain-markdown page list mirroring the XML sitemap
- [Robots.txt](https://ttslibrary.com/robots.txt): Crawling permissions and sitemap reference
- [LLMs.txt](https://ttslibrary.com/llms.txt): This file
- [LLMs Full](https://ttslibrary.com/llms-full.txt): Comprehensive documentation