> ## Documentation Index
> Fetch the complete documentation index at: https://koreai.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Support for Third-Party ASR, TTS, and Voice Biometrics

## Automatic Speech Recognition (ASR)

We support the following third-party service providers for [ASR services](/ai-for-service/channels/voice-gateway/configure-voice-gateway#voice-preferences):

| Type | ASR Provider | Deployment | Languages | Regions | Notes |
| - | - | - | - | - | - |
| Native | Microsoft Azure Speech Services ASR | Cloud & On-Prem | [100+ languages/locales](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support) | [Global Azure regions](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/regions) | Supports custom speech models and phrase lists for improving recognition accuracy. |
| Native | Google Cloud Speech-to-Text | Cloud | [125+ languages](https://docs.cloud.google.com/speech-to-text/docs/speech-to-text-supported-languages) | [Global](https://docs.cloud.google.com/speech-to-text/docs/locations) | Supports automatic punctuation and speaker diarization features. |
| Native | Amazon Transcribe | Cloud | [100+ languages/dialects](https://docs.aws.amazon.com/transcribe/latest/dg/supported-languages.html) | [Global AWS regions](https://docs.aws.amazon.com/general/latest/gr/transcribe.html) | Supports channel identification and domain-specific vocabularies. |
| Native | Deepgram | Cloud & On-Prem | [Multiple languages](https://developers.deepgram.com/docs/models-languages-overview) | Global | Low latency real-time transcription; custom model training supported. |
| Native | OpenAI ASR | Cloud | [100+ languages](https://github.com/openai/whisper/blob/main/whisper/tokenizer.py) | [Global](https://developers.openai.com/api/docs/supported-countries%5C) | Uses Whisper models for multilingual transcription and translation. |
| Native | Amivoice ASR | Cloud | [Japanese, English, Chinese, Korean](https://docs.amivoice.com/en/amivoice-api/manual/supported-languages) | - | - |
| Custom | Emotech ASR | Cloud | - | - | - |
| Custom | RTZR ASR | Cloud | - | - | - |

***

## Text to Speech (TTS)

We support the following third-party service providers for [TTS services](/ai-for-service/channels/voice-gateway/configure-voice-gateway#voice-preferences):

| Type | TTS Provider | Deployment | Languages | Regions | Notes | |
| - | - | - | - | - | - | - |
| Native | Microsoft Azure Speech Services TTS | Cloud & On-Prem | [100+ languages](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support) | [Global Azure regions](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/regions) | Neural voices and custom neural voice training available. | |
| Native | Google Cloud Text-to-Speech | Cloud | [50+ languages](https://docs.cloud.google.com/text-to-speech/docs/list-voices-and-types) | [Global](https://cloud.google.com/about/locations) | Includes WaveNet neural voices. | |
| Native | Amazon Polly | Cloud | [30+ languages](https://docs.aws.amazon.com/polly/latest/dg/supported-languages.html) | [Global AWS regions](https://docs.aws.amazon.com/general/latest/gr/Welcome.html) | Supports neural voices and SSML speech marks. | |
| Native | Deepgram TTS | Cloud & On-Prem | [Limited languages](https://developers.deepgram.com/docs/tts-models) | Global | Real-time conversational TTS optimized for voice agents. | |
| Native | ElevenLabs | Cloud | [30+ languages](https://elevenlabs.io/docs/overview/capabilities/text-to-speech#supported-languages) | Global | Human-like voices with stability, speed, and style controls. | |
| Native | OpenAI TTS | Cloud | [Multiple languages](https://developers.openai.com/api/docs/guides/text-to-speech#supported-languages) | Global | Natural sounding voices with limited voice options. | |
| Native | NvIdia Riva | On-Prem | [11+ languages](https://www.sarvam.ai/blogs/bulbul-v3) | - | - | |
| Custom | Sarvam TTS | - | - | - | - | |
| Custom | IST TTS | - | - | - | - | - |
| Custom | Emotech TTS | - | - | - | - | |
| Custom | MiniMax AI TTS | - | - | - | - | |

<Note>MiniMax AI TTS is a custom TTS provider that isn't available by default. To use it, contact [Support](https://support.kore.ai).</Note>

***

## Voice Biometrics

We support the following third-party service providers for voice biometrics:

| Type | Vendor | Engine | Deployment | Notes |
| - | - | - | - | - |
| Custom | ID R\&D | ID Voice | Cloud & On-Prem | Voice authentication and fraud detection engine. |

***


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.