Resemble AI Chatterbox Text To Speech

Usage-based pricing
ae_chatterbox_text_to_speech

Turn text into expressive, natural-sounding speech, optionally matching the style of a reference audio clip.

TTSAudio
Usage-based pricing

Pricing

The charge per call is (max(30 × Input text characters, 0)) AE credits. All applicable conditions are combined to calculate the total.

Input text characters are measured in thousands of characters. The same rate applies when using reference audio and speech controls.

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.cfgnumberNoNo parameter description.0.5
request_body.seedinteger | unknownNoUseful to control the reproducibility of the generated audio. Assuming all other properties didn't change, a fixed seed should always generate the exact same audio file. Set to 0 for random seed..—
request_body.textstringYesThe text to be converted to speech (maximum 5000 characters). You can additionally add the following emotive tags: <laugh>, <chuckle>, <sigh>, <cough>, <sniffle>, <groan>, <yawn>, <gasp>—
request_body.audio_urlstring | unknownNoOptional URL to an audio file to use as a reference for the generated speech. If provided, the model will try to match the style and tone of the reference audio.https://storage.googleapis.com/chatterbox-demo-samples/prompts/male_rickmorty.mp3
request_body.temperaturenumberNoTemperature for generation (higher = more creative).0.7
request_body.exaggerationnumberNoExaggeration factor for the generated speech (0.0 = no exaggeration, 1.0 = maximum exaggeration).0.25

Invocation example

Copy the request and explore its response example.

POST/agent-api/v1/tool/executeX-Api-Key

Submit first, then query with the returned task_id until the task completes.

Request coderequest.sh
curl --request POST \
  --url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_chatterbox_text_to_speech' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "exaggeration": 0.5,
      "seed": 0,
      "temperature": 0.8,
      "text": "I ate too many hamburgers."
    }
  }
}'
Response exampleresponse.json
JSON
{
  "description": "task accepted; poll the result via query_tool with this task_id",
  "query_tool": "ae_get_result",
  "status": "created",
  "task_id": "92486f89-4a90-4af4-b3a2-bc3372b7c250"
}

Guides using this tool

See how this tool fits into real workflows