Chatterbox Text To Speech

Chatterbox Text To Speech

Playground

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.

Features

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

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.

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.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-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 "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters