Class: ElevenLabsSpeechModel

Synthesize speech using the ElevenLabs Text to Speech API.

Both regular text-to-speech and full duplex text-to-speech streaming are supported.

See

• https://docs.elevenlabs.io/api-reference/text-to-speech
• https://docs.elevenlabs.io/api-reference/text-to-speech-websockets

Hierarchy

• AbstractModel<ElevenLabsSpeechModelSettings>

  ↳ ElevenLabsSpeechModel

Implements

• StreamingSpeechGenerationModel<ElevenLabsSpeechModelSettings>

Accessors

modelInformation

• get modelInformation(): ModelInformation

Returns

ModelInformation

Implementation of

StreamingSpeechGenerationModel.modelInformation

Inherited from

AbstractModel.modelInformation

Defined in

packages/modelfusion/src/model-function/AbstractModel.ts:17

---

modelName

• get modelName(): string

Returns

string

Overrides

AbstractModel.modelName

Defined in

packages/modelfusion/src/model-provider/elevenlabs/ElevenLabsSpeechModel.ts:85

---

settingsForEvent

• get settingsForEvent(): Partial<ElevenLabsSpeechModelSettings>

Returns settings that should be recorded in observability events. Security-related settings (e.g. API keys) should not be included here.

Returns

Partial<ElevenLabsSpeechModelSettings>

Implementation of

StreamingSpeechGenerationModel.settingsForEvent

Overrides

AbstractModel.settingsForEvent

Defined in

packages/modelfusion/src/model-provider/elevenlabs/ElevenLabsSpeechModel.ts:126

Constructors

constructor

• new ElevenLabsSpeechModel(settings): ElevenLabsSpeechModel

Parameters

Name	Type
settings	ElevenLabsSpeechModelSettings

Returns

ElevenLabsSpeechModel

Overrides

AbstractModel&lt;ElevenLabsSpeechModelSettings&gt;.constructor

Defined in

packages/modelfusion/src/model-provider/elevenlabs/ElevenLabsSpeechModel.ts:79

Methods

doGenerateSpeechStandard

▸ doGenerateSpeechStandard(text, options): Promise<Uint8Array>

Generates an mp3 audio Uint8Array that contains the speech for the given text.

Parameters

Name	Type
text	string
options	FunctionCallOptions

Returns

Promise<Uint8Array>

Implementation of

StreamingSpeechGenerationModel.doGenerateSpeechStandard

Defined in

packages/modelfusion/src/model-provider/elevenlabs/ElevenLabsSpeechModel.ts:134

---

doGenerateSpeechStreamDuplex

▸ doGenerateSpeechStreamDuplex(textStream): Promise<AsyncIterable<Delta<Uint8Array>>>

Parameters

Name	Type
textStream	AsyncIterable<string>

Returns

Promise<AsyncIterable<Delta<Uint8Array>>>

Implementation of

StreamingSpeechGenerationModel.doGenerateSpeechStreamDuplex

Defined in

packages/modelfusion/src/model-provider/elevenlabs/ElevenLabsSpeechModel.ts:138

---

withSettings

▸ withSettings(additionalSettings): ElevenLabsSpeechModel

The withSettings method creates a new model with the same configuration as the original model, but with the specified settings changed.

Parameters

Name	Type
additionalSettings	Partial<ElevenLabsSpeechModelSettings>

Returns

ElevenLabsSpeechModel

Example

const model = new OpenAICompletionModel({
  model: "gpt-3.5-turbo-instruct",
  maxGenerationTokens: 500,
});

const modelWithMoreTokens = model.withSettings({
  maxGenerationTokens: 1000,
});

Implementation of

StreamingSpeechGenerationModel.withSettings

Overrides

AbstractModel.withSettings

Defined in

packages/modelfusion/src/model-provider/elevenlabs/ElevenLabsSpeechModel.ts:245

Properties

provider

• Readonly provider: "elevenlabs"

Overrides

AbstractModel.provider

Defined in

packages/modelfusion/src/model-provider/elevenlabs/ElevenLabsSpeechModel.ts:83

---

settings

• Readonly settings: ElevenLabsSpeechModelSettings

Implementation of

StreamingSpeechGenerationModel.settings

Inherited from

AbstractModel.settings

Defined in

packages/modelfusion/src/model-function/AbstractModel.ts:7