Seedream 5.0 Pro 정식 출시 | 이미지 생성기에서 사용해보기 →

ByteDance Seed Speech TTS 2.0 API

bytedance /

ByteDance Seed Speech TTS 2.0 is a fast AI text-to-speech model that converts text into natural speech with multilingual voices, delivery controls, and MP3 or Opus output. Ready-to-use REST inference API for voice generation, narration, dubbing, virtual assistants, product demos, creator content, and professional TTS workflows with simple integration, no coldstarts, and affordable pricing.

text-to-audio
입력

대기 중

$0.03실행당·~33 / $1

예시전체 보기

관련 모델

README

ByteDance Seed Speech TTS 2.0

ByteDance Seed Speech TTS 2.0 converts text into speech with a wide selection of multilingual voice presets and controls for language, speed, pitch, volume, sample rate, and output format. It is suitable for narration, voiceovers, character voices, multilingual content, and production-ready speech synthesis workflows.

Why Choose This?

  • High-quality text-to-speech Generate natural-sounding speech from plain text.

  • Large voice preset library Choose from many built-in voices across English, Chinese, Japanese, Spanish, Indonesian, Portuguese, Korean, Italian, German, and French.

  • Multilingual support Use a language override or leave it empty for automatic language detection.

  • Fine-grained voice controls Adjust speed, volume, pitch, sample rate, and optional voice instructions.

  • Voice instruction support Add natural-language instructions for tone, emotion, pace, or volume without having that instruction spoken aloud.

  • Production-ready API Suitable for narration, audiobooks, short-form content, virtual assistants, localization, and voice-based creative workflows.

Parameters

ParameterRequiredDescription
textYesThe text to synthesize into speech.
voiceNoVoice preset to use for speech synthesis. Default: stokie_en.
voice_instructionNoOptional natural-language instruction for tone, emotion, pace, or volume. It is not spoken aloud.
output_formatNoOutput audio format. Supported values: mp3, opus. Default: mp3.
sample_rateNoSample rate of the output audio in Hz. Supported values: 8000, 16000, 22050, 24000, 32000, 44100, 48000. Default: 24000.
speedNoSpeech speed. Range: 0.5–2. Default: 1.
volumeNoSpeech volume. Range: 0.5–2. Default: 1.
pitchNoVoice pitch shift in semitones. Range: -12–12. Default: 0.
languageNoOptional language override. Leave unset for automatic language detection.

How to Use

  1. Enter your text — provide the text you want to synthesize.
  2. Choose a voice — select the preset that best fits your use case.
  3. Add a voice instruction (optional) — guide emotion, pacing, tone, or delivery style.
  4. Set audio controls (optional) — adjust speed, volume, pitch, and sample rate.
  5. Choose output format — select mp3 or opus.
  6. Set language (optional) — leave it empty for auto-detection, or choose a specific language.
  7. Submit — run the model and download the generated speech audio.

Example Voice Instruction

Warm, calm, confident narration with a slightly slower pace and soft expressive tone.

Pricing

Pricing is based on the length of the input text.

Text LengthCost
1–1000 chars$0.03
1001–2000 chars$0.06
2001–3000 chars$0.09
3001–4000 chars$0.12
4001–5000 chars$0.15

Billing Rules

  • Pricing is $0.03 per started 1000 characters
  • Character count is rounded up in blocks of 1000
  • Minimum billed length is 1 block
  • voice, voice_instruction, output_format, sample_rate, speed, volume, pitch, and language do not affect pricing

Best Use Cases

  • Narration — Generate voiceovers for videos, explainers, and presentations.
  • Multilingual content — Produce speech in multiple languages with preset voices.
  • Character voices — Create stylized spoken performances with different voice presets.
  • Localized media — Adapt content for different languages and markets.
  • Audio production — Build speech assets for apps, games, assistants, and creator workflows.

Pro Tips

  • Use voice_instruction when you want more expressive control without changing the text itself.
  • Keep speed near 1 for natural speech, then adjust only if needed.
  • Use a fixed language when auto-detection may be ambiguous.
  • Try several voice presets before settling on one for a recurring project.
  • Choose a higher sample rate when output quality matters more than file size.

Notes

  • text is required.
  • voice_instruction affects delivery style but is not spoken aloud.
  • language can be left empty for automatic language detection.
  • Pricing depends only on input text length.
  • Character count is billed in started 1000-character blocks.

Related Models

  • ByteDance Seed speech workflows — Useful when you need other speech generation or voice-related capabilities.
  • Voice cloning workflows — Useful when you need a reusable custom voice identity instead of preset voices.
  • Audio generation workflows — Useful when you need music or sound generation instead of speech synthesis.
참고:이 웹사이트는 제3자가 제공하는 AI 모델을 사용합니다.

Seed Speech Tts 2.0 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seed-speech-tts-2.0 with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Seed Speech Tts 2.0 below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "text": "A clear example input",
    "voice": "stokie_en",
    "output_format": "mp3",
    "sample_rate": 24000,
    "speed": 1,
    "volume": 1,
    "pitch": 0,
    "language": "zh"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seed-speech-tts-2.0" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/bytedance/seed-speech-tts-2.0";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "text": "A clear example input",
        "voice": "stokie_en",
        "output_format": "mp3",
        "sample_rate": 24000,
        "speed": 1,
        "volume": 1,
        "pitch": 0,
        "language": "zh"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "text": "A clear example input",
    "voice": "stokie_en",
    "output_format": "mp3",
    "sample_rate": 24000,
    "speed": 1,
    "volume": 1,
    "pitch": 0,
    "language": "zh"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/bytedance/seed-speech-tts-2.0", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Seed Speech Tts 2.0 API — Frequently asked questions

What is the Seed Speech Tts 2.0 API?

Seed Speech Tts 2.0 is a ByteDance model for audio generation, exposed as a REST API on WaveSpeedAI. ByteDance Seed Speech TTS 2.0 is a fast AI text-to-speech model that converts text into natural speech with multilingual voices, delivery controls, and MP3 or Opus output. Ready-to-use REST inference API for voice generation, narration, dubbing, virtual assistants, product demos, creator content, and professional TTS workflows with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Seed Speech Tts 2.0 API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seed-speech-tts-2.0.

How much does Seed Speech Tts 2.0 cost per run?

Seed Speech Tts 2.0 starts at $0.030 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Seed Speech Tts 2.0 accept?

Key inputs: `language`, `output_format`, `pitch`, `sample_rate`, `speed`, `text`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seed-speech-tts-2.0.

How long does Seed Speech Tts 2.0 take to generate?

Median end-to-end generation time on WaveSpeedAI is around 7 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Seed Speech Tts 2.0 outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (ByteDance). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

ByteDance Seed Speech TTS 2.0 API | WaveSpeedAI