ByteDanceSeed Audio Multilingual API

Name: Seed Audio Multilingual API
Price: 0.1875 USD
Author: ByteDance

Synthesize natural speech in 20 languages — pick a named voice or clone one from a reference audio.

Prompt

Reference inputs

Billed at this model’s published rate.

Result

Your generations will appear here

Other models from ByteDance

Same vendor, same API call — the differences are below.

Model	Use case	Price	Resolution	Duration	Added
ByteDance OmniHuman 2.0	Image → Video	from $0.077 / sec	—	—	Oct 2026
Seedream 5.0 Flash	Text → Image	from $0.0198 / gen	1K · 2K	—	Sep 2026
Seedance 2.5	Text → Video	from $0.1234 / sec	480p · 720p · 1080p	4–30s	Aug 2026
Seedance 2.5 Video Edit	Video → Video	from $0.1234 / sec	480p · 720p · 1080p	—	Aug 2026
Seedance 2.5 Video Extend	Video → Video	from $0.1234 / sec	480p · 720p · 1080p	4–30s	Aug 2026
Seedream 4.7	Text → Image	from $0.0225 / gen	1K · 2K · 4K	—	Aug 2026
ByteDance Video Enhance	Video → Video	from $0.0038 / sec	source · 720p · 1080p …	—	Jul 2026
Seed Audio	Text → Speech	from $0.1875 / min	—	—	Jul 2026

Install the SDK

TypeScript targets Node 20+ and ships with types; Python needs 3.10+ and is async. Over REST there is nothing to install: call https://api.picsart.com from any HTTP client.

bash

npm install @picsart/ai-sdk

Authenticate

Send your Picsart API key as a bearer token. The SDK does it for you once the client is created.

import { createClient } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY, // sent as: Authorization: Bearer <key>
  apiUrl: 'https://api.picsart.com',
});

python

import os

from picsart_ai_sdk import create_client

ai = create_client(
    api_key=os.environ["PICSART_API_KEY"],  # sent as: Authorization: Bearer <key>
    api_url="https://api.picsart.com",
)

Make a request

Call the model by its id. Over REST, one endpoint serves every model: POST /workflows/v1/models/execute with the model id and its input in the body. The outer params is the envelope every workflow takes; the inner one is this model's input, with the same names generate() takes.

import { createClient } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

const result = await ai.generate('seed-audio-1.0-multilingual', {
  prompt: "A serene mountain lake at golden hour, ultra detailed"
});

console.log(result.url); // audio URL

python

import asyncio
import os

from picsart_ai_sdk import create_client


async def main() -> None:
    async with create_client(
        api_key=os.environ["PICSART_API_KEY"],
        api_url="https://api.picsart.com",
    ) as ai:
        result = await ai.generate("seed-audio-1.0-multilingual", {
            "prompt": "A serene mountain lake at golden hour, ultra detailed",
        })

        print(result.url)  # audio URL


asyncio.run(main())

bash

curl -X POST 'https://api.picsart.com/workflows/v1/models/execute' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "model": "seed-audio-1.0-multilingual",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed"
    }
  }
}'

Async (submit & poll)

This model can run longer than the sync limit (~20s). generate() waits for you; to hold on to the job instead, submit it and poll. Over REST, send it to /workflows/v1/models/submit and poll /workflows/v1/models/{taskId}/result until response.status is COMPLETED or FAILED.

import { createClient } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

// Returns the generation id at once — store it to pick the job up later.
const generationId = await ai.submit('seed-audio-1.0-multilingual', {
  prompt: "A serene mountain lake at golden hour, ultra detailed"
});

// Polls until the job completes; throws if it fails or is cancelled.
const result = await ai.result('seed-audio-1.0-multilingual', generationId);

console.log(result.url); // audio URL

python

import asyncio
import os

from picsart_ai_sdk import create_client


async def main() -> None:
    async with create_client(
        api_key=os.environ["PICSART_API_KEY"],
        api_url="https://api.picsart.com",
    ) as ai:
        # Returns the generation id at once — store it to pick the job up later.
        generation_id = await ai.submit("seed-audio-1.0-multilingual", {
            "prompt": "A serene mountain lake at golden hour, ultra detailed",
        })

        # Polls until the job completes; raises ApiError if it fails or is cancelled.
        result = await ai.result("seed-audio-1.0-multilingual", generation_id)

        print(result.url)  # audio URL


asyncio.run(main())

bash

# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/v1/models/submit' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "model": "seed-audio-1.0-multilingual",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed"
    }
  }
}'
# → { "status": "success", "response": { "id": "task_abc123" } }

# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/v1/models/task_abc123/result' \
  -H 'Authorization: Bearer $PICSART_API_KEY'

Parameters

10 parameters, the same for the SDK and for the inner params over REST. Required ones must be supplied; the rest fall back to their defaults.

Parameter	Type	Required	Default	Details
`prompt` The text to speak. For music and sound effects, what to make, in plain language.	`text`	yes	`—`	max 3000 chars
`voiceId` The voice to speak with, by id from the voices catalog.	`catalog`	no	`en_male_tim_uranus_bigtts`	options from bytedance/v1/catalog/voices (seed-audio-1.0-multilingual)
`audioUrls` Input audio files, as URLs.	`file (audio[])`	no	`—`	—
`imageUrls` Input images, as URLs: the image to edit, or references for subject, style or composition.	`file (image[])`	no	`—`	—
`format` File format of the result.	`enum`	no	`wav`	wav, mp3, pcm, ogg_opus
`sampleRate` Sample rate of the audio, in Hz.	`enum`	no	`44100`	8000, 16000, 24000, 32000, 44100, 48000
`speechRate` Speaking speed, as a percentage change from normal.	`range`	no	`0`	-50–100
`loudnessRate` Loudness, as a percentage change from normal.	`range`	no	`0`	-50–100
`pitchRate` Pitch shift. 0 is the voice's own pitch.	`range`	no	`0`	-12–12
`aigcWatermark` Whether the result carries the vendor's AI watermark.	`boolean`	no	`false`	—

Response

generate() resolves once the job completes. An audio URL. Over REST the output is at response.result, inside the gateway's status envelope with the task id, its status and the amount charged.

json

{
  "items": [
    {
      "url": "https://cdn.picsart.com/…/result"
    }
  ],
  "model": "seed-audio-1.0-multilingual"
}

json

{
  "status": "success",
  "response": {
    "id": "task_abc123",
    "status": "COMPLETED",
    "result": {
      "url": "https://cdn.picsart.com/…/result",
      "items": [
        {
          "url": "https://cdn.picsart.com/…/result"
        }
      ],
      "model": "seed-audio-1.0-multilingual"
    }
  }
}

Overview

Alongside the unified model APIs, we expose compatibility APIs that take each vendor's original parameters exactly as the vendor defines them — nothing renamed, nothing reshaped on the way through.

That makes them the shortest path onto Picsart if you already work with the vendor directly: the request bodies you've already written keep working as they are. You keep their parameter names and defaults, and you get the vendor's full parameter set rather than the subset that is shared across every model.

The cost is that a request is written for one vendor — switching models later means rewriting it, and results come back in the vendor's own shape. When you'd rather write once and change models freely, use the unified API.

Make a request

Call the workflow with ai.apis.run() in TypeScript or Python, or hit /workflows/{workflow}/execute directly — params is passed through untouched either way.

These endpoints are addressed by workflow name rather than model id: the one in this model's header, since one model runs as one workflow. Authentication is unchanged — your Picsart API key as a bearer token (see Authentication).

import { createClient, ApiRunMode } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

// Calls the 'bytedance/text-to-speech' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('bytedance/text-to-speech', {
  text_prompt: "A serene mountain lake at golden hour, ultra detailed"
}, {
  mode: ApiRunMode.SYNC,
});

console.log(result); // workflow-specific output
console.log(usage?.credits); // amount charged, in $

python

import asyncio
import os

from picsart_ai_sdk import ApiRunMode, create_client


async def main() -> None:
    async with create_client(
        api_key=os.environ["PICSART_API_KEY"],
        api_url="https://api.picsart.com",
    ) as ai:
        # Calls the 'bytedance/text-to-speech' workflow directly — params are sent as-is.
        response = await ai.apis.run("bytedance/text-to-speech", {
            "text_prompt": "A serene mountain lake at golden hour, ultra detailed",
        }, mode=ApiRunMode.SYNC)

        print(response["result"])  # workflow-specific output
        print((response.get("usage") or {}).get("credits"))  # amount charged, in $


asyncio.run(main())

bash

curl -X POST 'https://api.picsart.com/workflows/bytedance/text-to-speech/execute' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "text_prompt": "A serene mountain lake at golden hour, ultra detailed"
  }
}'

Async (submit & poll)

This model can run longer than the sync limit (~20s). In the SDK, ai.apis.run() with ApiRunMode.ASYNC polls for you; over HTTP, submit and poll yourself.

import { createClient, ApiRunMode } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

// mode: ASYNC submits the job and polls under the hood — you just await.
const { result } = await ai.apis.run('bytedance/text-to-speech', {
  text_prompt: "A serene mountain lake at golden hour, ultra detailed"
}, {
  mode: ApiRunMode.ASYNC,
});

console.log(result);

python

import asyncio
import os

from picsart_ai_sdk import ApiRunMode, create_client


async def main() -> None:
    async with create_client(
        api_key=os.environ["PICSART_API_KEY"],
        api_url="https://api.picsart.com",
    ) as ai:
        # mode=ASYNC submits the job and polls under the hood — you just await.
        response = await ai.apis.run("bytedance/text-to-speech", {
            "text_prompt": "A serene mountain lake at golden hour, ultra detailed",
        }, mode=ApiRunMode.ASYNC)

        print(response["result"])


asyncio.run(main())

bash

# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/bytedance/text-to-speech/submit' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "text_prompt": "A serene mountain lake at golden hour, ultra detailed"
  }
}'
# → { "status": "success", "response": { "id": "wf_abc123" } }

# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/bytedance/text-to-speech/wf_abc123/result' \
  -H 'Authorization: Bearer $PICSART_API_KEY'

Parameters

6 parameters, sent inside params. These are the vendor's own names, so they line up one-for-one with the vendor's documentation. Required ones must be supplied; the rest fall back to their defaults.

Parameter	Type	Required	Default	Details
`model` Model version identifier. Both variants share the same request shape, limits, voice-cloning support and audio knobs — they differ only in language coverage and timing control, and each is billed under its own pricing entry. - `seed-audio-1.0` (default) — English, Chinese only. - `seed-audio-1.0-multilingual` — 20 languages: English, Chinese, Japanese, Korean, Mexican Spanish, Castilian Spanish, Indonesian, German, Brazilian Portuguese, French, Thai, Vietnamese, Malay, Filipino, Italian, Russian, Dutch, Polish, Turkish, Swedish. Also advertised as supporting timing control (pacing the speech to fit a given time window); the vendor API reference documents no request parameter for it, so it is expressed through `text_prompt` — see the BytePlus docs for the prompt syntax. Pick `seed-audio-1.0-multilingual` for any language other than English/Chinese.	`string`	no	`seed-audio-1.0`	`seed-audio-1.0seed-audio-1.0-multilingual`
`text_prompt` Prompt used to synthesize audio, or the text to be synthesized. Up to 3000 characters. Reference audio is addressed as @Audio1, @Audio2, ... matching the order of audio references. When an image reference is used, text_prompt may contain only the text to be synthesized.	`string`	yes	`—`	—
`references` Reference resources. Omit for text-only generation. Up to 3 audio references (speaker/audio_data/audio_url) OR exactly 1 image reference (image_data/image_url); audio and image references cannot be mixed.	`ReferenceResource[]`	no	`—`	—
└`speaker` Speaker ID — a predefined BytePlus TTS 2.0 voice or a cloned voice id. Provide exactly one of speaker, audio_data, or audio_url. Any valid BytePlus voice id is accepted (the list below is a sample, not a whitelist). The `en_` / `zh_` voices work with both models; the other languages require `seed-audio-1.0-multilingual`. Speaking a voice's own language gives the best result. Examples: - `en_male_tim_uranus_bigtts` — Tim — English, clear friendly mid-range male - `en_female_dacey_uranus_bigtts` — Dacey — English, warm engaging female - `en_female_stokie_uranus_bigtts` — Stokie — English, casual expressive young female - `zh_male_liufei_uranus_bigtts` — Felix — Chinese, clear energetic male - `zh_female_qingxinnvsheng_uranus_bigtts` — Celeste — Chinese, fresh clear female - `ja_female_minimi_uranus_bigtts` — Minimi — Japanese, sweet young female (multilingual only) - `ko_male_m03_uranus_bigtts` — Minho — Korean, professional narrator (multilingual only) - `de_male_seven_uranus_bigtts` — Sven — German, steady confident male (multilingual only) - `fr_male_usseau_uranus_bigtts` — Usseau — French, crisp articulate male (multilingual only) - `es_male_felipe_uranus_bigtts` — Felipe — Mexican Spanish, upbeat young male (multilingual only) - `it_male_enzo_uranus_bigtts` — Enzo — Italian, warm charismatic male (multilingual only) - `pt_male_martins_uranus_bigtts` — Martins — Brazilian Portuguese, expressive male (multilingual only) - `ru_male_pavel_uranus_bigtts` — Pavel — Russian, natural narrative male (multilingual only) - `ru_female_af07_uranus_bigtts` — Amelia — Russian, gentle graceful female (multilingual only) - `id_male_han_uranus_bigtts` — Han — Indonesian, smooth friendly male (multilingual only) - `ms_male_naim_uranus_bigtts` — Naim — Malay, calm refined male (multilingual only) - `tl_female_annika_uranus_bigtts` — Annika — Filipino female (multilingual only) - `th_female_bv568_neutral_uranus_bigtts` — Mildred — Thai, calm neutral female (multilingual only) - `vi_female_linh_uranus_bigtts` — Linh — Vietnamese, crisp decisive female (multilingual only)	`string`	no	`—`	e.g. `en_male_tim_uranus_bigtts`
└`audio_data` Base64-encoded reference audio (<=30s, <=10MB; wav/mp3/pcm/ogg_opus).	`string`	no	`—`	—
└`audio_url` Reference audio URL (<=30s, <=10MB; wav/mp3/pcm/ogg_opus).	`string`	no	`—`	—
└`image_data` Base64-encoded reference image (<=10MB; jpeg/png/webp). Cannot be combined with audio references.	`string`	no	`—`	—
└`image_url` Reference image URL (<=10MB; jpeg/png/webp). Cannot be combined with audio references.	`string`	no	`—`	—
`audio_config` Output audio configuration.	`object`	no	`—`	—
└`format` Output format. Default wav.	`string`	no	`—`	`wavmp3pcmogg_opus`
└`sample_rate` Output sample rate (Hz). Default: wav/pcm 40000, mp3 44100.	`number`	no	`—`	`80001600024000320004410048000`
└`speech_rate` Speech rate. Range [-50, 100]: 100 = 2.0x, -50 = 0.5x. Default 0.	`number`	no	`—`	—
└`loudness_rate` Volume. Range [-50, 100]: 100 = 2.0x, -50 = 0.5x. Default 0.	`number`	no	`—`	—
└`pitch_rate` Pitch. Range [-12, 12]. Default 0.	`number`	no	`—`	—
`watermark` Watermark configuration.	`object`	no	`—`	—
└`aigc_watermark` Explicit watermark: adds an audio rhythm marker at the end. Default false.	`boolean`	no	`—`	—
└`aigc_metadata` Implicit watermark metadata added to the audio header.	`object`	no	`—`	—
└`enable` Enable the implicit watermark. Default false.	`boolean`	no	`—`	—
└`content_producer`	`string`	no	`—`	—
└`produce_id`	`string`	no	`—`	—
└`content_propagator`	`string`	no	`—`	—
└`propagate_id`	`string`	no	`—`	—
`options` Options controlling safety checks and drive integration	`object`	no	`—`	—
└`safety_checks` Safety check settings	`object`	no	`—`	—
└`enabled` Whether to run content moderation. Defaults to true.	`boolean`	no	`—`	—
└`drive` Save result to Picsart Drive	`object`	no	`—`	—
└`name` File name in Picsart Drive	`string`	yes	`—`	—
└`attributes` Custom attributes to attach to the file	`object`	no	`—`	—
└`folder` Target folder in Picsart Drive	`object`	no	`—`	—
└`inputs_transformation` Input transformation settings	`object`	no	`—`	—
└`downscale_oversized_images` Whether to downscale oversized input images. Defaults to false.	`boolean`	no	`—`	—

Response

Over HTTP the output arrives inside a status envelope, at response.result. ai.apis.run() unwraps that envelope for you and resolves to { result, usage } instead. Either way the result itself is the vendor's own shape.

json

{
  "result": {
    "url": "https://cdn.picsart.com/…/result.mp3",
    "duration": 0,
    "format": "…",
    "driveFile": {
      "id": "wf_abc123"
    }
  }
}

json

{
  "status": "success",
  "response": {
    "result": {
      "url": "https://cdn.picsart.com/…/result.mp3",
      "duration": 0,
      "format": "…",
      "driveFile": {
        "id": "wf_abc123"
      }
    }
  }
}

ByteDanceSeed Audio Multilingual API

Params

Result

Other models from ByteDance

Install the SDK

Authenticate

Make a request

Async (submit & poll)

Parameters

Response

Overview

Make a request

Async (submit & poll)

Parameters

Response

Rates