Providers and Services Supported
The Intelligent AI Connector (IAC) currently supports Oracle Cloud Infrastructure (OCI) as the AI provider, with the Speech-to-Text (STT) service for real-time audio transcription.
The following table lists the supported provider and service combinations:
Table 4-1 Supported Providers and Services
| Provider | Identifier | Service | Description |
|---|---|---|---|
| Oracle Cloud Infrastructure | oci | Speech-to-Text | Real-time audio transcription via OCI Speech service. |
The OCI Realtime Speech service offers 2 models:
- ORACLE (native)
- WHISPER (openAI model through OCI)
Permissible Values
modelType = "WHISPER" (Provider - OCI) [OpenAI Model in OCI]
Table 4-2 Whisper Model Configuration Parameters
| Parameter | Allowed Values | Default | Description |
|---|---|---|---|
| modelType | "WHISPER" | "WHISPER" | Required for Whisper. |
| languageCode | "auto", "af", "am", "ar", "as", "az", "ba", "be", "bg", "bn", "bo", "br", "bs", "ca", "cs", "cy", "da", "de", "el", "en", "es", "et", "eu", "fa", "fi", "fo", "fr", "gl", "gu", "ha", "haw", "he", "hi", "hr", "ht", "hu", "hy", "id", "is", "it", "ja", "jv", "ka", "kk", "km", "kn", "ko", "la", "lb", "ln", "lo", "lt", "lv", "mg", "mi", "mk", "ml", "mn", "mr", "ms", "mt", "my", "ne", "nl", "nn", "no", "oc", "pa", "pl", "ps", "pt", "ro", "ru", "sa", "sd", "si", "sk", "sl", "sn", "so", "sq", "sr", "su", "sv", "sw", "ta", "te", "tg", "th", "tk", "tl", "tr", "tt", "uk", "ur", "uz", "vi", "yi", "yo", "zh" | "en" | Language code for transcription. Use "auto" for automatic detection. |
| encoding | "audio/raw;rate=16000", "audio/raw;rate=8000", "audio/raw;rate=8000;codec=mulaw", "audio/raw;rate=8000;codec=alaw" | "audio/raw;rate=16000" | Audio encoding format. |
| modelDomain | "GENERIC" | "GENERIC" | Only GENERIC is allowed. |
| punctuation | "NONE", "AUTO" | "NONE" | Controls automatic punctuation in transcription output. |
| isAckEnabled | true, false | false | Enables or disables acknowledgment responses. |
modelType = "ORACLE" (Provider - OCI)
Table 4-3 Common Parameters
| Key | Permissible Values | Default Value (on OCI) | Note |
|---|---|---|---|
| modelType | "ORACLE" | "ORACLE" | Model type |
| encoding | "audio/raw;rate=16000", "audio/raw;rate=8000", "audio/raw;rate=8000;codec=mulaw", "audio/raw;rate=8000;codec=alaw" | "audio/raw;rate=16000" | Audio Encoding |
| modelDomain | "GENERIC", "MEDICAL" | "GENERIC" | Model parameters are described below. |
Table 4-4 Parameters for modelDomain = "GENERIC"
| Key | Permissible Values | Default Value (on OCI) | Note |
|---|---|---|---|
| languageCode | "en-US", "es-ES", "pt-BR", "en-GB", "en-AU", "en-IN", "hi-IN", "fr-FR", "de-DE", "it-IT" | "en-US" | Only these values allowed |
| punctuation | "NONE", "AUTO" | "NONE" | Whether to automatically add punctuation |
| isAckEnabled | true, false | false | |
| partialSilenceThresholdInMs | 0–2000 (integer) | OCI Service defined | Validated by bounds check |
| finalSilenceThresholdInMs | 0–5000 (integer) | OCI Service defined | Validated by bounds check |
| stabilizePartialResults | "NONE", "LOW", "MEDIUM", "HIGH" | "NONE" |
Table 4-5 Parameters for modelDomain = "MEDICAL"
| Key | Permissible Values | Default Value (on OCI) | Note |
|---|---|---|---|
| languageCode | "en-US" | "en-US" | Only en-US |
| punctuation | "NONE", "AUTO", "SPOKEN" | "NONE" | "SPOKEN" only for MEDICAL |
| isAckEnabled | true, false | false | |
| partialSilenceThresholdInMs | 0–2000 (integer) | OCI Service defined | Validated by bounds check |
| finalSilenceThresholdInMs | 0–5000 (integer) | OCI Service defined | Validated by bounds check |
| stabilizePartialResults | "NONE", "LOW", "MEDIUM", "HIGH" | "NONE" |
The following validations are also performed:
partialSilenceThresholdInMsshould not be greater than finalSilenceThresholdInMs- For the ORACLE model, click here to see a mapping between what encoding is needed for which language: