Inference Logoinference shell

DramaBox Text-to-Speech

Expressive text-to-speech with voice cloning. The prompt controls emotion, laughs, sighs, pauses and delivery.

text to speechvoice cloning
run in browser →run via API
run with your agent
# install belt
$curl -fsSL https://cli.inference.sh | sh
# sign in (or set INFERENCE_API_KEY on a headless machine)
$belt login
# view schema & details
$belt app get infsh/dramabox
# run
$belt app run infsh/dramabox --input '{"prompt":"A woman speaks warmly, \"Hello, how are you today?\" She laughs, \"Hahaha, it is so good to see you!\""}'
maker
infsh
category
audio
input → output
text → speech
price
GPU time, billed per millisecond
runs via
api, javascript and python sdk, belt cli, mcp
updated
2026-09-09

api reference

about

expressive text-to-speech with voice cloning. the prompt controls emotion, laughs, sighs, pauses and delivery.

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
1import os2from inferencesh import inference34client = inference(api_key=os.environ["INFERENCE_API_KEY"])567result = client.run({8        "app": "infsh/dramabox",9        "input": {10            "prompt": "A woman speaks warmly, \"Hello, how are you today?\" She laughs, \"Hahaha, it is so good to see you!\""11        }12    })1314print(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
1import os2from inferencesh import inference34client = inference(api_key=os.environ["INFERENCE_API_KEY"])567# stream=True yields updates as they arrive8for update in client.run({9        "app": "infsh/dramabox",10        "input": {11            "prompt": "A woman speaks warmly, \"Hello, how are you today?\" She laughs, \"Hahaha, it is so good to see you!\""12        }13    }, stream=True):14    if update.get("progress"):15        print(f"progress: {update['progress']}%")16    if update.get("output"):17        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/dramabox",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/dramabox",3    "input": {4        "prompt": "A woman speaks warmly, \"Hello, how are you today?\" She laughs, \"Hahaha, it is so good to see you!\""5    },6    "webhook": "https://your-server.com/webhook"7}, wait=False)

webhook payload

your endpoint receives a JSON POST with the task result:

json
1{2  "event": "task.completed",3  "timestamp": "2024-01-15T10:30:05Z",4  "data": {5    "id": "task_abc123",6    "short_id": "abc123",7    "status": 10,8    "status_text": "completed",9    "output": { ... },10    "created_at": "2024-01-15T10:30:00Z",11    "updated_at": "2024-01-15T10:30:05Z"12  }13}
eventstringtask.completed, task.failed or task.cancelled
timestampstringiso timestamp of the delivery
data.idstringtask id
data.short_idstringshort task id
data.statusnumberterminal status (10=completed, 11=failed, 12=cancelled, 13=rejected)
data.status_textstringthe status as a word: completed, failed or cancelled
data.outputobjecttask output (when completed)
data.errorstringerror message (when failed, omitted otherwise)
data.session_idstringsession id (when the task ran in a session, omitted otherwise)
data.created_atstringiso timestamp
data.updated_atstringiso timestamp

5. schema

input

promptstring*

scene-style prompt: <speaker description>, "<dialogue>" <stage direction> "<more dialogue>". text inside quotes is spoken; text outside quotes directs delivery (e.g. she sighs deeply.). laughs and sounds go inside quotes as one word ("hahaha", "mmmm", "ugh"). end the prompt at the last closing quote. long prompts are chunked automatically.

example: "A woman speaks warmly, \"Hello, how are you today?\" She laughs, \"Hahaha, it is so good to see you!\""
voice_referencestring(file)

optional voice reference to clone (10+ seconds recommended; first 10 s are used). match the speaker description to the reference's gender and age.

cfg_scalenumber

classifier-free guidance. lower = more natural, higher = more text-faithful.

default: 2.5min:1max:10
stg_scalenumber

skip-token guidance scale.

default: 1.5min:0max:5
durationnumber

target output length in seconds. 0 = estimate automatically from the prompt.

default: 0min:0max:300
duration_multipliernumber

headroom applied to the auto-estimated duration (ignored when duration is set).

default: 1.1min:0.5max:2
seedinteger

random seed for reproducible output.

default: 42min:0

output

audiostring(file)*

generated speech (wav, 48 khz, watermarked with resemble perth)

duration_secondsnumber*

length of the generated audio in seconds

other audio apps

Fish Audio Drama 3

fish-audio/drama-3

$50.00/1M UTF-8 bytes

Eleven Flash v2.5

elevenlabs/eleven-flash-v2-5

$0.04/1K characters

Eleven Multilingual v2

elevenlabs/eleven-multilingual-v2

$0.08/1K characters

Eleven v3

elevenlabs/eleven-v3

$0.08/1K characters

Eleven v4 Turbo

elevenlabs/eleven-v4-turbo

$0.04/1K characters

more from infsh

HTTP Request

infsh/http

from $0.00000277/sec

Markdown to Word Converter

infsh/markdown-to-word

from $0.00000277/sec

Harrier OSS v1 Text Embeddings

infsh/harrier-oss-v1

GPU time, billed per millisecond

DeepSeek OCR 2

infsh/deepseek-ocr-2

GPU time, billed per millisecond

new models

  1. VACE

    pruna/vace

    video$0.40/video

  2. P-Video-Animate

    pruna/p-video-animate

    video$0.03/sec 720p, $0.06/sec 1080p

  3. P-Video-Upscale

    pruna/p-video-upscale

    videoStd: $0.01/sec 720p, $0.02 1080p, $0.04 2k, $0.08 4k; high fps 2x

  4. P-Video-2-Pro-Avatar

    pruna/p-video-2-pro-avatar

    video$0.02/sec 480p, $0.04/sec 768p, $0.06/sec 1080p, $0.08/sec 2k, $0.12/sec 4k

  5. P-Video-2-Pro-Reference

    pruna/p-video-2-pro-reference

    videoOutput: cost $0.015-$0.105/sec, speed $0.02-$0.115/sec. Ref video: $0.03-$0.06/sec. Ref img: $0.005/img. Ref audio: $0.0015-$0.0025/sec

ready to run DramaBox Text-to-Speech?

try in browserbrowse all apps

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.