Text-to-speech (Json)

1 from hume import HumeClient 2 from hume.tts import FormatMp3, PostedContextWithUtterances, PostedUtterance 3 4 client = HumeClient( 5 api_key="YOUR_API_KEY", 6 ) 7 client.tts.synthesize_json( 8 utterances=[ 9 PostedUtterance( 10 text="Beauty is no quality in things themselves: It exists merely in the mind which contemplates them.", 11 description="Middle-aged masculine voice with a clear, rhythmic Scots lilt, rounded vowels, and a warm, steady tone with an articulate, academic quality.", 12 ) 13 ], 14 context=PostedContextWithUtterances( 15 utterances=[ 16 PostedUtterance( 17 text="How can people see beauty so differently?", 18 description="A curious student with a clear and respectful tone, seeking clarification on Hume's ideas with a straightforward question.", 19 ) 20 ], 21 ), 22 format=FormatMp3(), 23 num_generations=1, 24 )

1 { 2 "generations": [ 3 { 4 "audio": "//PExAA0DDYRvkpNfhv3JI5JZ...etc.", 5 "duration": 7.44225, 6 "encoding": { 7 "format": "mp3", 8 "sample_rate": 24000 9 }, 10 "file_size": 120192, 11 "generation_id": "795c949a-1510-4a80-9646-7d0863b023ab", 12 "snippets": [ 13 [ 14 { 15 "audio": "//PExAA0DDYRvkpNfhv3JI5JZ...etc.", 16 "audio_format": "mp3", 17 "generation_id": "795c949a-1510-4a80-9646-7d0863b023ab", 18 "id": "37b1b1b1-1b1b-1b1b-1b1b-1b1b1b1b1b1b", 19 "text": "Beauty is no quality in things themselves: It exists merely in the mind which contemplates them." 20 } 21 ] 22 ] 23 } 24 ], 25 "request_id": "66e01f90-4501-4aa0-bbaf-74f45dc15aa725906" 26 }

Synthesizes one or more input texts into speech using the specified voice. If no voice is provided, a novel voice will be generated dynamically. Optionally, additional context can be included to influence the speech’s style and prosody.

The response includes the base64-encoded audio and metadata in JSON format.

Headers

X-Hume-Api-KeystringRequired

Request

This endpoint expects an object.

utteranceslist of objectsRequired

Utterances to be converted to speech output.

contextobjectOptional

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

formatobjectOptional

Specifies the output audio file format.

num_generationsintegerOptional>=1<=5Defaults to 1

Number of generations of the audio to produce.

split_utterancesbooleanOptionalDefaults to true

Controls how audio output is segmented in the response.

When enabled (true), input utterances are automatically split into natural-sounding speech segments.
When disabled (false), the response maintains a strict one-to-one mapping between input utterances and output snippets.

This setting affects how the snippets array is structured in the response, which may be important for applications that need to track the relationship between input text and generated audio segments. When setting to false, avoid including utterances with long text, as this can result in distorted output.

Response

Successful Response

generationslist of objects

request_idstringOptional

A unique ID associated with this request for tracking and troubleshooting. Use this ID when contacting support for troubleshooting assistance.

Headers

Request

Response

Errors