How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

ElevenLabs Speech Engine API

Low-latency, real-time speech generation endpoints.

ElevenLabs Speech Engine API is one of 50 APIs that ElevenLabs publishes on the APIs.io network, described by a machine-readable OpenAPI specification and an AsyncAPI event-driven specification.

Tagged areas include Speech Engine. The published artifact set on APIs.io includes an OpenAPI specification, an API reference, API documentation, authentication docs, rate-limit docs, and an AsyncAPI specification.

This API exposes 5 operations across 2 paths, and defines 51 schemas. It is described by OpenAPI 3.2.0, at version 1.0.

Requests are made against the base URL https://api.elevenlabs.io.

5 operations 2 paths 51 schemas 1 DELETE2 GET1 PATCH1 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
1.0
Base URL
https://api.elevenlabs.io
Resource Areas
1

Paths & Operations 5

Across 2 paths, the API surfaces 5 operations — 1 DELETE, 2 GET, 1 PATCH, 1 POST. Each is listed below with its method, path, parameters, and response codes.

Speech Engine 5

Low-latency, real-time speech generation endpoints.

GET
/v1/speech-engine
List Speech Engines
list_speech_engines 6 params → 200422
POST
/v1/speech-engine
Create Speech Engine
create_speech_engine 1 param body → 201422
GET
/v1/speech-engine/{speech_engine_id}
Get Speech Engine
get_speech_engine 2 params → 200422
PATCH
/v1/speech-engine/{speech_engine_id}
Update Speech Engine
update_speech_engine 2 params body → 200422
DELETE
/v1/speech-engine/{speech_engine_id}
Delete Speech Engine
delete_speech_engine 2 params → 204422

Schemas 51

The contract defines 51 schemas that model the data the API accepts and returns. The most detailed are SpeechEngineResponse (16 properties), TTSConversationalConfig-Input (14 properties), TTSConversationalConfig-Output (14 properties), CreateSpeechEngineRequest (13 properties). Each schema is shown below with its type and property counts.

ASRInputFormat
string
TurnModel
string
Version of the turn detection model to use.
ConversationHistoryRedactionConfig
object
2 properties
AgentDefinitionSource
string
TTSModelFamily
string
VADConfig
object
1 property
TTSOptimizeStreamingLatency
integer
SupportedVoice
object
9 properties 2 required
ValidationError
object
3 properties 3 required
TTSConversationalModel
string
TTSConversationalConfig-Input
object
14 properties
PrivacyConfig-Input
object
7 properties
FileInputConfig
object
3 properties
ASRProvider
string
SpeechEngineConversationInitiationClientDataConfig
object
1 property
SuggestedAudioTag
object
2 properties 1 required
AgentMetadataDBModel
object
4 properties 2 required
BackgroundSoundPresetId
string
Predefined background sound preset identifiers.
ConvAISecretLocator
object
Used to reference a secret from the agent's secret store.
1 property 1 required
ListSpeechEnginesResponse
object
3 properties 2 required
SortDirection
string
PrivacyConfig-Output
object
7 properties
EffectsSpec-Output
object
Filter preset, distance (proximity EQ), and environment (convolution reverb).
6 properties 6 required
AgentCallLimits
object
3 properties
AgentSortBy
string
TTSOutputFormat
string
BackgroundSoundSourceType
string
The type of background sound source.
TurnEagerness
string
Agent's eagerness to respond. Higher values make agent wait for higher turn probability.
EffectsSpec-Input
object
Filter preset, distance (proximity EQ), and environment (convolution reverb).
6 properties
ResourceAccessInfo
object
6 properties 4 required
HTTPValidationError
object
1 property
ASRConversationalConfig
object
4 properties
SpeechEngineResponse
object
16 properties 15 required
ClientEvent
string
SpellingPatience
string
Controls if the agent should be more patient when user is spelling numbers and named entities.
TurnMode
string
UpdateSpeechEngineRequest
object
13 properties
ConversationConfig-Output
object
9 properties
TTSConversationalConfig-Output
object
14 properties
SpeechEngineConfig
object
2 properties 1 required
BackgroundSoundConfig
object
4 properties
CreateSpeechEngineRequest
object
13 properties 1 required
ASRQuality
string
TextNormalisationType
string
Method for converting numbers to words before sending to TTS
DTMFInputConfig
object
Configuration for DTMF (keypad) input collection during phone calls.
3 properties
ConfigEntityType
string
Entity types for the API configuration. This enum contains all valid entity type configurations that users can specify: - Parent types (e.g., "name", "financia…
ConversationConfig-Input
object
9 properties
BaseTurnConfig
object
13 properties
SpeechEngineSummaryResponse
object
6 properties 6 required
PydanticPronunciationDictionaryVersionLocator
object
A locator for other documents to be able to reference a specific dictionary and it's version. This is a pydantic version of PronunciationDictionaryVersionLocat…
2 properties 2 required
ConvAIDynamicVariable
object
Used to reference a dynamic variable.
1 property 1 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

elevenlabs-speech-engine-api-openapi.yml Raw ↑

Other APIs ElevenLabs publishes across the network.

elevenlabs Agents API
elevenlabs Audio Isolation API
elevenlabs Audio Native API
elevenlabs Conversations API
elevenlabs Dubbing API
elevenlabs Dubbing Resources API
elevenlabs Instant Voice Cloning API
elevenlabs Knowledge Base API
elevenlabs Music Generation API
elevenlabs Professional Voice Cloning API
elevenlabs Speech to Speech API
elevenlabs Speech to Text API
Where this information came from

This is an independent, third-party profile of ElevenLabs Speech Engine 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.