reference.md

Reference

Tts

client.tts.bytes({ ...params }) -> core.BinaryResponse

📝 Description

The easiest way to generate text-to-speech audio. Not suitable for latency-sensitive applications.

🔌 Usage

await client.tts.bytes({
    transcript: "Hello, World!",
    voice: {
        id: "samantha"
    }
});

⚙️ Parameters

request: Respeecher.BytesGenerationRequest

requestOptions: TtsClient.RequestOptions

client.tts.sse({ ...params }) -> core.Stream

📝 Description

Stream text-to-speech audio as JSONL (JSON lines) objects over HTTP. A less performant alternative to WebSockets, without text input streaming.

🔌 Usage

const response = await client.tts.sse({
    transcript: "Hello, World!",
    voice: {
        id: "samantha"
    }
});
for await (const item of response) {
    console.log(item);
}

⚙️ Parameters

request: Respeecher.StreamingGenerationRequest

requestOptions: TtsClient.RequestOptions

Voices

client.voices.list() -> Respeecher.Voice[]

📝 Description

List of available voices with IDs and metadata.

🔌 Usage

await client.voices.list();

⚙️ Parameters

requestOptions: VoicesClient.RequestOptions