Text-to-Speech (File) | Hume API

Authentication

X-Hume-Api-Key string

API Key authentication via header

Request

This endpoint expects an object.

• utterances list of objects Required

A list of Utterances to be converted to speech output.

An Utterance is a unit of input for Octave, and includes input text, an optional description to serve as the prompt for how the speech should be delivered, an optional voice specification, and additional controls to guide delivery for speed and trailing_silence.

• context object or null Optional

Utterances to use as context for generating consistent speech style and prosody across multiple requests. These will not be converted to speech output.

• format object Optional Defaults to {"type":"mp3"}

Specifies the output audio file format.

• include_timestamp_types list of enums Optional Defaults to []

The set of timestamp types to include in the response. Only supported for Octave 2 requests.

Allowed values: word, phoneme

• num_generations integer Optional 1-5 Defaults to 1

Number of audio generations to produce from the input utterances.

• split_utterances boolean Optional Defaults to true

Controls how audio output is segmented in the response.

• strip_headers boolean Optional Defaults to false

If enabled, the audio for all the chunks of a generation, once concatenated together, will constitute a single audio file.

• temperature double or null Optional 0.1-1

Sampling temperature for the speech generation model. Higher values increase variation; lower values increase consistency.

• version enum Optional

Selects the Octave model version used to synthesize speech for this request.

• instant_mode boolean Optional Defaults to true

Enables ultra-low latency streaming, significantly reducing the time until the first audio chunk is received.

Response

OK

Errors

422

Unprocessable Entity Error