Oracle AI Service Speech API is one of 378 APIs that Oracle publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include AIServiceSpeech. The published artifact set on APIs.io includes an OpenAPI specification and an API reference.
This API exposes
19 operations
across 13 paths,
and defines 35 schemas.
It is described by OpenAPI 3.2.0, at version 20220101.
Requests are made against a single base URL, https://$SWAGGER_HOST_URL/20220101.
19 operations13 paths35 schemas2 DELETE7 GET8 POST2 PUT
Metadata
The identity and technical contract details declared by the specification.
Specification
OpenAPI 3.2.0
API Version
20220101
Base URL
https://{host}:{port}/ords/
Resource Areas
1
Paths & Operations 19
Across 13 paths, the API surfaces 19 operations — 2 DELETE, 7 GET, 8 POST, 2 PUT. Each is listed below with its method, path, parameters, and response codes.
AIServiceSpeech 19
POST
/actions/realtimeSessionToken
Creates a session and sends a token so that users can authenticate themselves. An alternate way to authenticate is by skipping this endpoint and directly using the credentials in the SDK.
The contract defines 35 schemas that model the data the API accepts and returns. The most detailed are TranscriptionJob (23 properties), TranscriptionJobSummary (16 properties), TranscriptionTask (15 properties), Customization (15 properties). Each schema is shown below with its type and property counts.
TranscriptionJobCollection
object
Results of a Transcription Job search. Contains both TranscriptionJobSummary items and other information, such as metadata.
1 property1 required
CustomizationSummary
object
Summary of the Customization.
11 properties3 required
VoiceSummary
object
Details related to the voice available for the given language code and voice type.
10 properties5 required
Customization
object
Description of a Customization.
15 properties3 required
Error
object
Error Information.
2 properties2 required
OutputLocation
object
OCI Object Storage Location.
3 properties3 required
TtsConfiguration
object
Speech configuration for TTS API.
1 property1 required
RealtimeSessionToken
object
The response from the realtime session token endpoint that creates the auth token to be used with the realtime speech service.
5 properties3 required
CustomizationDatasetDetails
object
Customization Training Dataset
1 property1 required
VoiceCollection
object
Results of the voices available as speaker Ids for given language code and voice type combination.
1 property1 required
InputLocation
object
The location of the input(s).
1 property1 required
CustomizationReferencedEntities
object
Entities referenced by top level customization.
3 properties
TranscriptionTask
object
Description of Transcription Task.
15 properties1 required
CreateCustomizationDetails
object
The information about the new Customization.
8 properties3 required
TranscriptionSettings
object
Processes to perform on the generated transcription.
2 properties
SynthesizeSpeechDetails
object
Input JSON to get audio inference from TTS Service.
5 properties1 required
CreateTranscriptionJobDetails
object
The information about new Transcription Job.
10 properties3 required
ChangeTranscriptionJobCompartmentDetails
object
Details for changing the compartment of a transcription job.
1 property1 required
CreateRealtimeSessionTokenDetails
object
Request sent to the realtime authentication endpoint in order to obtain the auth token.
3 properties1 required
ObjectLocation
object
A location in Object Storage that is uniquely identified by namespace name, bucket name and object name.
3 properties3 required
Diarization
object
Speaker diarization is a combination of speaker segmentation and speaker clustering. Provide diarization details to enable this feature.
2 properties
UpdateCustomizationDetails
object
The information to be updated.
7 properties
TranscriptionFilter
object
Transcription Filter.
1 property1 required
TranscriptionTaskCollection
object
Results of a Transcription Task search. Contains both TranscriptionTaskSummary items and other information, such as metadata.
1 property1 required
AudioFormatDetails
object
Audio format details.
4 properties
TranscriptionJobSummary
object
Summary of the Transcription Job.
16 properties3 required
CustomizationModelDetails
object
Details of the base ASR model to train a Customization for.
2 properties
ChangeCustomizationCompartmentDetails
object
Details for changing the compartment of a Customization.
1 property1 required
TranscriptionNormalization
object
Information to Normalize generated transcript.
2 properties
TtsAudioConfig
object
Use this schema to specify handling of audio response. If audioConfig is not provided, raw response is handed over for the user to handle.
1 property1 required
TranscriptionJob
object
Description of Transcription Job.
23 properties5 required
UpdateTranscriptionJobDetails
object
The information to be updated.
4 properties
CustomizationCollection
object
Results of a Customization search. Contains both CustomizationSummary items and other information, such as metadata.
1 property1 required
TranscriptionModelDetails
object
Model details.
4 properties
TranscriptionTaskSummary
object
Summary of the Transcription Task.
10 properties2 required
Specification
The full machine-readable OpenAPI contract behind this narrative.
Every API here is available over the API and to AI agents over MCP. APIs is not yet its own endpoint on the v1 API. Reach this content through network search and the tag graph, or the MCP server below.
Installs https://mcp.apievangelist.com/mcp in Claude, Cursor, VS Code and the rest — one button, every client.
MCP tools for apis
4 tools reach this content
search_api_evangelistSearch every content type across the network at once.
find_relatedThe shared-tag relevance graph — what else covers this.
get_tagEverything one tag labels, across all content types.
guide_topicPRO — a curated bundle for a topic: area, guidance, rules, papers, stories, services.
A second provider on the same verified email joins the account you already have.
Your account
ⓘWhere this information came from
This is an independent, third-party profile of Oracle AI Service Speech API, published by
API Evangelist. We do not operate, host, resell, or
support these APIs, and we are not affiliated with or endorsed by the company unless stated above.
Everything here is built from publicly available information — the company's own site,
developer portal, documentation, public repositories, and the specifications it publishes for public use.
Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's
public API artifacts, scored against a published rubric. They are not certifications,
endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and
you do not need to justify the request. A removed company is recorded as unrated, never scored
zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy → On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.