apps/infsh/higgs-audio

higgs-audio

Generates speech from text with advanced, expressive audio quality.

run in browser run via API

run with your agent

# install belt

$curl -fsSL https://cli.inference.sh | sh

# view schema & details

$belt app get infsh/higgs-audio

# run

$belt app run infsh/higgs-audio

api reference

about

generates speech from text with advanced, expressive audio quality.

1. calling the api

install the client

the client provides a convenient way to interact with the api.

bash

1pip install inferencesh

setup your api key

set INFERENCE_API_KEY as an environment variable. get your key from settings → api keys.

bash

1export INFERENCE_API_KEY="inf_your_key"

run and get result

submit a request and wait for the final result. best for batch processing or when you don't need progress updates.

python

1from inferencesh import inference23client = inference()456result = client.run({7        "app": "infsh/higgs-audio",8        "input": {}9    })1011print(result["output"])

stream live updates

get real-time progress updates as the task runs. ideal for showing progress bars, partial results, or long-running tasks.

python

1from inferencesh import inference23client = inference()456# stream=True yields updates as they arrive7for update in client.run({8        "app": "infsh/higgs-audio",9        "input": {}10    }, stream=True):11    if update.get("progress"):12        print(f"progress: {update['progress']}%")13    if update.get("output"):14        print(f"output: {update['output']}")

2. authentication

the api uses api keys for authentication. see the authentication docs for detailed setup instructions.

3. files

file inputs are automatically handled by the sdk. you can pass local paths, urls, or base64 data.

automatic upload

the python sdk automatically detects local file paths and uploads them. urls are passed through as-is.

python

1# local file paths are automatically uploaded2result = client.run({3    "app": "infsh/higgs-audio",4    "input": {5        "image": "/path/to/local/image.png",  # detected & uploaded6        "audio": "https://example.com/audio.mp3",  # url passed through7    }8})

manual upload

you can also upload files manually and use the returned url.

python

1# upload and get a hosted URL2file = client.files.upload("/path/to/file.png")3print(file.uri)  # https://cloud.inference.sh/...

4. webhooks

get notified when a task completes by providing a webhook url. when the task reaches a terminal state (completed, failed, or cancelled), a POST request is sent to your url with the task result.

python

1result = client.run({2    "app": "infsh/higgs-audio",3    "input": {},4    "webhook": "https://your-server.com/webhook"5}, wait=False)

webhook payload

your endpoint receives a JSON POST with the task result:

json

1{2  "id": "task_abc123",3  "status": 9,4  "output": { ... },5  "error": "",6  "session_id": null,7  "created_at": "2024-01-15T10:30:00Z",8  "updated_at": "2024-01-15T10:30:05Z"9}

idstring— task id

statusnumber— terminal status (9=completed, 10=failed, 11=cancelled)

outputobject— task output (when completed)

errorstring— error message (when failed)

session_idstring— session id (if using sessions)

created_atstring— iso timestamp

updated_atstring— iso timestamp

5. schema

input

transcriptstring*

the text to convert to speech

temperaturenumber

the value used to module the next token probabilities

default: 1

top_kinteger

the number of highest probability vocabulary tokens to keep for top-k-filtering

default: 50

top_pnumber

top-p sampling parameter

default: 0.95

max_new_tokensinteger

the maximum number of new tokens to generate

default: 2048

seedinteger

random seed for generation

ref_audiostring

voice reference audio name (e.g., 'belinda', 'broom_salesman') or comma-separated for multi-speaker

scene_promptstring

scene description prompt for context

chunk_methodstring

chunking method: 'speaker', 'word', or none

chunk_max_word_numinteger

maximum words per chunk when using word chunking

default: 200

chunk_max_num_turnsinteger

maximum turns per chunk when using speaker chunking

default: 1

generation_chunk_buffer_sizeinteger

maximum chunks to keep in buffer

ras_win_leninteger

ras sampling window length (0 to disable)

default: 7

ras_win_max_num_repeatinteger

maximum ras window repeats

default: 2

ref_audio_in_system_messageboolean

include reference audio description in system message

default: false

output

audio_outputobject*

the generated audio file

ready to run higgs-audio?

try in browser browse all tools

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.