Seedream 5.0 Pro अब लाइव है | Image Generator में आज़माएं →
साइन इन

Chatterbox Text to Speech API

chatterbox /

Chatterbox Text to Speech is a fast AI TTS model that converts text into expressive speech with optional reference audio, emotive tags, and delivery controls. Ready-to-use REST inference API for voice generation, narration, character dialogue, dubbing, virtual assistants, creator content, and professional text-to-speech workflows with simple integration, no coldstarts, and affordable pricing.

text-to-audio
इनपुट

निष्क्रिय

$0.03प्रति रन·~33 / $1

उदाहरणसभी देखें

संबंधित मॉडल

README

Chatterbox Text-to-Speech

Chatterbox Text-to-Speech converts text into expressive speech with optional reference-audio guidance and adjustable generation controls. It is suitable for narration, character voice prototyping, creator voiceovers, and other prompt-free speech generation workflows where you want simple text input plus style tuning.

Why Choose This?

  • Text-to-speech generation
    Turn written text into spoken audio with a simple workflow.

  • Optional reference voice guidance
    Add reference_audio when you want the generated voice to follow a particular tone or vocal style.

  • Expressiveness control
    Use exaggeration to make the delivery more restrained or more expressive.

  • Generation tuning
    Adjust temperature and cfg for different levels of variation and prompt adherence.

  • Production-ready API
    Useful for voiceovers, demos, creator content, character voice testing, and narration workflows.

Parameters

ParameterRequiredDescription
textYesText to synthesize into speech.
reference_audioNoOptional reference audio used to guide the generated voice style.
exaggerationNoControls how expressive or exaggerated the generated delivery sounds.
temperatureNoControls randomness and variation in the generated speech.
cfgNoGuidance setting used to influence generation behavior.

How to Use

  1. Enter your text — provide the script you want the model to speak.
  2. Add reference audio (optional) — upload a voice sample if you want style guidance.
  3. Adjust exaggeration (optional) — increase it for more expressive delivery or keep it lower for a calmer tone.
  4. Adjust temperature and cfg (optional) — tune generation behavior if needed.
  5. Submit — run the model and download the generated speech audio.

Example Text

Welcome to wavespeed! It's nice to meet you!

Pricing

Pricing is based on the length of the input text.

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

Billing Rules

  • Pricing is $0.025 per started 1000 characters
  • Character count is rounded up in blocks of 1000
  • Minimum billed length is 1 block
  • reference_audio, exaggeration, temperature, and cfg do not affect pricing

Best Use Cases

  • Narration — Generate spoken audio for explainers, demos, and presentations.
  • Creator voiceovers — Produce quick voice tracks for short-form content.
  • Character voice prototyping — Explore delivery styles with optional reference voice guidance.
  • Product and onboarding content — Create friendly spoken intros or guidance clips.
  • Speech testing workflows — Compare different expressive settings from the same script.

Pro Tips

  • Keep the input text clean and naturally punctuated for better rhythm.
  • Add reference_audio only when you want stronger voice-style guidance.
  • Lower exaggeration for calm narration and raise it for more dramatic delivery.
  • Increase temperature when you want more variation, or keep it lower for steadier results.
  • Test short lines first before generating longer scripts.

Notes

  • text is required.
  • Pricing depends only on input text length.
  • Character count is billed in started 1000-character blocks.
  • Optional tuning controls affect delivery style, but not price.

Related Models

  • Other text-to-speech workflows — Useful when you need different voice style, pricing, or synthesis behavior.
  • Voice cloning workflows — Useful when you need a reusable voice identity instead of prompt-guided speech generation.
  • Audio generation workflows — Useful when you need music or sound generation instead of spoken voice.
नोट:यह वेबसाइट तृतीय पक्षों द्वारा प्रदान किए गए AI मॉडलों का उपयोग करती है।

Text To Speech API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/chatterbox/text-to-speech 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 Text To Speech below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "text": "A clear example input",
    "exaggeration": 0.25,
    "temperature": 0.7,
    "cfg": 0.5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/chatterbox/text-to-speech" \
  -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/chatterbox/text-to-speech";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "text": "A clear example input",
        "exaggeration": 0.25,
        "temperature": 0.7,
        "cfg": 0.5
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "exaggeration": 0.25,
    "temperature": 0.7,
    "cfg": 0.5
}

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/chatterbox/text-to-speech", 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)

Text To Speech API — Frequently asked questions

What is the Text To Speech API?

Text To Speech is a Chatterbox model for audio generation, exposed as a REST API on WaveSpeedAI. Chatterbox Text to Speech is a fast AI TTS model that converts text into expressive speech with optional reference audio, emotive tags, and delivery controls. Ready-to-use REST inference API for voice generation, narration, character dialogue, dubbing, virtual assistants, creator content, and professional text-to-speech 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 Text To Speech 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/chatterbox/chatterbox-text-to-speech.

How much does Text To Speech cost per run?

Text To Speech 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 Text To Speech accept?

Key inputs: `cfg`, `exaggeration`, `reference_audio`, `temperature`, `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/chatterbox/chatterbox-text-to-speech.

How long does Text To Speech take to generate?

Median end-to-end generation time on WaveSpeedAI is around 9 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 Text To Speech outputs commercially?

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

Chatterbox Text to Speech API | WaveSpeedAI