# OmniVoice TTS

> Run OmniVoice TTS by infsh online or via API. GPU time, billed per millisecond, no setup.

**URL:** https://inference.sh/apps/infsh/omnivoice
**Last updated:** 2026-11-03

---

Zero-shot text-to-speech with voice cloning for 600+ languages.

- app: `infsh/omnivoice`
- 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

## omnivoice API Guide

### About
zero-shot text-to-speech with voice cloning for 600+ languages.

### Get an API Key
Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`.

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

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Run and Get Result
Submit a request and wait for the final result.

```python
import os
from inferencesh import inference

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

## version @4p314p3n pinned
result = client.run({
        "app": "infsh/omnivoice@4p314p3n",
        "input": {
            "text": "text"
        }
    })

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

#### Stream Live Updates
Get real-time progress updates as the task runs.

```python
import os
from inferencesh import inference

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

## version @4p314p3n pinned
## stream=True yields updates as they arrive
for update in client.run({
        "app": "infsh/omnivoice@4p314p3n",
        "input": {
            "text": "text"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

#### Run in the Background
Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled).

```python
import os
from inferencesh import inference, TaskStatus

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

## returns as soon as the task is created
task = client.run({
        "app": "infsh/omnivoice@4p314p3n",
        "input": {
            "text": "text"
        }
    }, wait=False)

## later: read its current state
state = client.tasks.get(task["id"]).data
if state["status"] == TaskStatus.COMPLETED:
    print(state["output"])
```

### 2. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "infsh/omnivoice@4p314p3n",
    "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/...
```

### 3. Schema

#### Input
- **text** (string) *required*: Text to convert to speech. Supports non-verbal tags like [laughter], [sigh], and pronunciation control.
- **mode** (string): Generation mode: 'voice_cloning' (clone from reference audio), 'voice_design' (describe voice attributes), or 'auto' (model picks a voice)
- **ref_audio** (string): Reference audio for voice cloning (3-10 seconds recommended). Required for voice_cloning mode.
- **ref_text** (string): Transcription of the reference audio. If omitted, Whisper ASR auto-transcribes it.
- **instruct** (string): Voice design attributes for voice_design mode. Comma-separated: e.g. 'female, low pitch, british accent'. Supports gender, age, pitch, accent, whisper.
- **num_step** (integer): Number of diffusion steps. Lower (16) = faster, higher (32) = better quality.
- **speed** (number): Speaking speed factor. >1.0 = faster, <1.0 = slower.
- **duration** (number): Fixed output duration in seconds. Overrides speed if set.

#### Output
- **audio** (string): Generated speech audio file (WAV, 24kHz)

## other audio apps

- [Fish Audio Drama 3](https://inference.sh/apps/fish-audio/drama-3.md): $50.00/1M UTF-8 bytes
- [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

## faq

### how much does OmniVoice TTS cost?

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

### how do I run OmniVoice TTS via api?

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

### who makes OmniVoice TTS?

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

### can my agent use OmniVoice TTS?

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 OmniVoice TTS?

other audio apps on inference shell include Fish Audio Drama 3, Eleven Flash v2.5, Eleven Multilingual v2, Eleven v3. they run through the same api, so switching is a one-line change.