OpenAITTS
OpenAI TTS provider using the official OpenAI SDK for text-to-speech synthesis.
Defined in: src/providers/tts/openai/OpenAITTS.ts:211
OpenAI TTS provider using the official OpenAI SDK for text-to-speech synthesis.
Remarks
This is a REST-based provider: each synthesize() call makes a single HTTP request to the OpenAI TTS API and returns the complete audio response as a Blob. It supports both the standard tts-1 (fast) and tts-1-hd (high quality) models, with six available voices and five audio formats.
The lifecycle is:
- Construct with OpenAITTSConfig
- Call
initialize()to load the OpenAI SDK and create the client - Call
synthesize(text)to convert text to audio - Call
dispose()to release resources
Audio flow: Text -> OpenAI REST API -> Complete audio Blob
Example
import { OpenAITTS } from 'composite-voice';
const tts = new OpenAITTS({
apiKey: 'sk-xxxxxxxxxxxx',
model: 'tts-1',
voice: 'nova',
responseFormat: 'mp3',
});
await tts.initialize();
const audioBlob = await tts.synthesize('Hello, world!');
// Play the audio blob, e.g., via an <audio> element
See
- RestTTSProvider - The base class this provider extends.
- OpenAITTSConfig - Configuration options for this provider.
Extends
RestTTSProvider
Constructors
Constructor
new OpenAITTS(config, logger?): OpenAITTS;
Defined in: src/providers/tts/openai/OpenAITTS.ts:229
Creates a new OpenAITTS provider instance.
Parameters
| Parameter | Type | Description |
|---|---|---|
config | OpenAITTSConfig | Configuration for the OpenAI TTS provider. |
logger? | Logger | Optional logger instance for debug and diagnostic output. |
Returns
OpenAITTS
Example
const tts = new OpenAITTS({
apiKey: 'sk-xxxxxxxxxxxx',
voice: 'alloy',
});
Overrides
RestTTSProvider.constructor
Properties
| Property | Modifier | Type | Default value | Description | Overrides | Inherited from | Defined in |
|---|---|---|---|---|---|---|---|
audioCallback? | protected | (chunk) => void | undefined | Callback registered by the SDK or consumer to receive audio chunks. Set via onAudio. | - | RestTTSProvider.audioCallback | src/providers/base/BaseTTSProvider.ts:79 |
config | public | OpenAITTSConfig | undefined | TTS-specific provider configuration. | RestTTSProvider.config | - | src/providers/tts/openai/OpenAITTS.ts:212 |
initialized | protected | boolean | false | Tracks whether initialize has completed successfully. | - | RestTTSProvider.initialized | src/providers/base/BaseProvider.ts:97 |
logger | protected | Logger | undefined | Scoped logger instance for this provider. | - | RestTTSProvider.logger | src/providers/base/BaseProvider.ts:94 |
metadataCallback? | protected | (metadata) => void | undefined | Callback registered by the SDK or consumer to receive audio metadata. Set via onMetadata. | - | RestTTSProvider.metadataCallback | src/providers/base/BaseTTSProvider.ts:85 |
roles | readonly | readonly ProviderRole[] | undefined | TTS providers cover the 'tts' pipeline role by default. | - | RestTTSProvider.roles | src/providers/base/BaseTTSProvider.ts:70 |
type | readonly | ProviderType | undefined | Communication transport this provider uses ('rest' or 'websocket'). | - | RestTTSProvider.type | src/providers/base/BaseProvider.ts:74 |
Methods
assertReady()
protected assertReady(): void;
Defined in: src/providers/base/BaseProvider.ts:255
Guard that throws if the provider has not been initialized.
Returns
void
Remarks
Call at the start of any method that requires the provider to be ready.
Throws
Error Thrown with a descriptive message when initialized is false.
Inherited from
RestTTSProvider.assertReady
dispose()
dispose(): Promise<void>;
Defined in: src/providers/base/BaseProvider.ts:154
Clean up resources and dispose of the provider.
Returns
Promise<void>
Remarks
Delegates to the subclass hook onDispose and resets the initialized flag. If the provider is not initialized, the call is a no-op.
Throws
Re-throws any error raised by onDispose.
Inherited from
RestTTSProvider.dispose
emitAudio()
protected emitAudio(chunk): void;
Defined in: src/providers/base/BaseTTSProvider.ts:138
Emit a synthesized audio chunk to the registered callback.
Parameters
| Parameter | Type | Description |
|---|---|---|
chunk | AudioChunk | The audio chunk to emit. |
Returns
void
Remarks
Subclasses call this method for each chunk of audio produced during synthesis. If no callback has been registered the chunk is silently dropped.
Inherited from
RestTTSProvider.emitAudio
emitMetadata()
protected emitMetadata(metadata): void;
Defined in: src/providers/base/BaseTTSProvider.ts:154
Emit audio metadata to the registered callback.
Parameters
| Parameter | Type | Description |
|---|---|---|
metadata | AudioMetadata | The audio metadata to emit. |
Returns
void
Remarks
Typically called once at the start of synthesis when the provider knows the output format. If no callback has been registered the metadata is silently dropped.
Inherited from
RestTTSProvider.emitMetadata
getConfig()
getConfig(): TTSProviderConfig;
Defined in: src/providers/base/BaseTTSProvider.ts:165
Get a shallow copy of the current TTS configuration.
Returns
A new TTSProviderConfig object.
Inherited from
RestTTSProvider.getConfig
initialize()
initialize(): Promise<void>;
Defined in: src/providers/base/BaseProvider.ts:127
Initialize the provider, making it ready for use.
Returns
Promise<void>
Remarks
Calls the subclass hook onInitialize. If the provider has already been initialized the call is a no-op.
Throws
ProviderInitializationError Thrown when onInitialize rejects. The original error is wrapped with the provider class name for diagnostics.
Inherited from
RestTTSProvider.initialize
isReady()
isReady(): boolean;
Defined in: src/providers/base/BaseProvider.ts:178
Check whether the provider has been initialized and is ready.
Returns
boolean
true when initialize has completed successfully and dispose has not yet been called.
Inherited from
RestTTSProvider.isReady
onAudio()
onAudio(callback): void;
Defined in: src/providers/base/BaseTTSProvider.ts:109
Register a callback to receive synthesized audio chunks.
Parameters
| Parameter | Type | Description |
|---|---|---|
callback | (chunk) => void | Function invoked with each AudioChunk. |
Returns
void
Remarks
All TTS providers — regardless of transport — deliver audio through this callback. CompositeVoice registers it during pipeline setup so that audio data flows into the AudioPlayer.
Inherited from
RestTTSProvider.onAudio
onConfigUpdate()
protected onConfigUpdate(_config): void;
Defined in: src/providers/base/BaseProvider.ts:242
Hook called after updateConfig merges new values.
Parameters
| Parameter | Type | Description |
|---|---|---|
_config | Partial<BaseProviderConfig> | The partial configuration that was merged. |
Returns
void
Remarks
The default implementation is a no-op. Override in subclasses to react to runtime configuration changes (e.g. reconnect with a new API key).
Inherited from
RestTTSProvider.onConfigUpdate
onDispose()
protected onDispose(): Promise<void>;
Defined in: src/providers/tts/openai/OpenAITTS.ts:294
Disposes the provider and releases the OpenAI client.
Returns
Promise<void>
Overrides
RestTTSProvider.onDispose
onInitialize()
protected onInitialize(): Promise<void>;
Defined in: src/providers/tts/openai/OpenAITTS.ts:246
Initializes the OpenAI client by dynamically importing the SDK.
Returns
Promise<void>
Remarks
The openai package is loaded dynamically as a peer dependency. If using proxyUrl, the client is configured with a placeholder API key and the proxy URL as the base URL. The client is created with dangerouslyAllowBrowser: true to enable browser usage.
Throws
ProviderInitializationError if neither apiKey nor proxyUrl is configured.
Throws
ProviderInitializationError if the openai package is not installed.
Throws
ProviderInitializationError if any other initialization error occurs.
Overrides
RestTTSProvider.onInitialize
onMetadata()
onMetadata(callback): void;
Defined in: src/providers/base/BaseTTSProvider.ts:124
Register a callback to receive audio metadata.
Parameters
| Parameter | Type | Description |
|---|---|---|
callback | (metadata) => void | Function invoked with AudioMetadata when available. |
Returns
void
Remarks
Metadata (sample rate, encoding, channels, etc.) helps the AudioPlayer configure playback correctly. Providers may emit metadata once at the start of synthesis but are not required to.
Inherited from
RestTTSProvider.onMetadata
synthesize()
synthesize(text): Promise<Blob>;
Defined in: src/providers/tts/openai/OpenAITTS.ts:314
Synthesizes text to audio using the OpenAI TTS REST API.
Parameters
| Parameter | Type | Description |
|---|---|---|
text | string | The text to synthesize into speech. Maximum length depends on the OpenAI API limits (currently 4096 characters). |
Returns
Promise<Blob>
A Blob containing the synthesized audio in the configured format.
Remarks
Makes a single HTTP POST request to the OpenAI audio.speech.create endpoint. The complete audio response is returned as a Blob with the appropriate MIME type based on the configured responseFormat.
Throws
Error if the provider is not initialized or the OpenAI client is null.
Throws
Error if the OpenAI API request fails (network error, rate limit, etc.).
Overrides
RestTTSProvider.synthesize
updateConfig()
updateConfig(config): void;
Defined in: src/providers/base/BaseProvider.ts:201
Merge partial configuration updates into the current config.
Parameters
| Parameter | Type | Description |
|---|---|---|
config | Partial<BaseProviderConfig> | A partial configuration object whose keys will overwrite existing values. |
Returns
void
Remarks
After merging, the subclass hook onConfigUpdate is called so providers can react to changed values at runtime.
Inherited from
RestTTSProvider.updateConfig