# Higgs Audio

> Run Higgs Audio by infsh online or via API. Pay per run, no setup.

**URL:** https://inference.sh/apps/infsh/higgs-audio
**Last updated:** 2026-07-28

---

Generates speech from text with advanced, expressive audio quality.

- app: `infsh/higgs-audio`
- maker: [infsh](https://inference.sh/apps/infsh.md)
- category: [audio](https://inference.sh/apps/category/audio.md)
- input → output: text → speech
- tasks: [text to speech](https://inference.sh/apps/tag/text-to-speech.md), [voice cloning](https://inference.sh/apps/tag/voice-cloning.md)
- price: GPU time, billed per millisecond
- runs via: api, javascript and python sdk, belt cli, mcp

## higgs-audio API Guide

### About
generates speech from text with advanced, expressive audio quality.

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Setup Your API Key
Set `INFERENCE_API_KEY` as an environment variable. Get your key from settings → api keys.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

#### Run and Get Result

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])


result = client.run({
        "app": "infsh/higgs-audio@73pcxmgh",
        "input": {
            "transcript": "transcript"
        }
    })

print(result["output"])
```

#### Stream Live Updates

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])


## stream=True yields updates as they arrive
for update in client.run({
        "app": "infsh/higgs-audio@73pcxmgh",
        "input": {
            "transcript": "transcript"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

### 2. Authentication
The API uses API keys for authentication. See the authentication docs for detailed setup instructions.

### 3. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "infsh/higgs-audio@73pcxmgh",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

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

### 4. Schema

#### Input
- **transcript** (string) *required*: The text to convert to speech
- **temperature** (number): The value used to module the next token probabilities
- **top_k** (integer): The number of highest probability vocabulary tokens to keep for top-k-filtering
- **top_p** (number): Top-p sampling parameter
- **max_new_tokens** (integer): The maximum number of new tokens to generate
- **seed** (integer): Random seed for generation
- **ref_audio** (string): Voice reference audio name (e.g., 'belinda', 'broom_salesman') or comma-separated for multi-speaker
- **scene_prompt** (string): Scene description prompt for context
- **chunk_method** (string): Chunking method: 'speaker', 'word', or None
- **chunk_max_word_num** (integer): Maximum words per chunk when using word chunking
- **chunk_max_num_turns** (integer): Maximum turns per chunk when using speaker chunking
- **generation_chunk_buffer_size** (integer): Maximum chunks to keep in buffer
- **ras_win_len** (integer): RAS sampling window length (0 to disable)
- **ras_win_max_num_repeat** (integer): Maximum RAS window repeats
- **ref_audio_in_system_message** (boolean): Include reference audio description in system message

#### Output
- **audio_output** (string): The generated audio file

## other audio apps

- [Eleven Flash v2.5](https://inference.sh/apps/elevenlabs/eleven-flash-v2-5.md): $0.04/1K characters
- [Eleven Multilingual v2](https://inference.sh/apps/elevenlabs/eleven-multilingual-v2.md): $0.08/1K characters
- [Eleven v3](https://inference.sh/apps/elevenlabs/eleven-v3.md): $0.08/1K characters
- [Eleven v4 Turbo](https://inference.sh/apps/elevenlabs/eleven-v4-turbo.md): $0.04/1K characters
- [Eleven v4](https://inference.sh/apps/elevenlabs/eleven-v4.md): $0.08/1K characters

## faq

### how much does Higgs Audio cost?

GPU time, billed per millisecond. you pay per run from your inference shell credits. no subscription is required.

### how do I run Higgs Audio via api?

call infsh/higgs-audio with the javascript or python sdk, the rest api, or `belt app run infsh/higgs-audio` from a terminal. the api reference on this page lists every input.

### who makes Higgs Audio?

Higgs Audio is made by infsh and runs on inference shell. every infsh app is listed at https://inference.sh/apps/infsh.

### can my agent use Higgs Audio?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to Higgs Audio?

other audio apps on inference shell include Eleven Flash v2.5, Eleven Multilingual v2, Eleven v3, Eleven v4 Turbo. they run through the same api, so switching is a one-line change.