ElevenLabs TTS Multilingual V2
Usage-based pricing
ae_elevenlabs_tts_multilingual_v2
Turn text into natural-sounding speech with a chosen voice, language, speed, style controls, and optional word timestamps.
Usage-based pricing
Pricing
The charge per call is (max(120 × Text characters, 0)) AE credits. All applicable conditions are combined to calculate the total.
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
request_body | object | Yes | No parameter description. | — |
request_body.text | string | Yes | The text to convert to speech | — |
request_body.speed | number | No | Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality. | 1 |
request_body.style | number | No | Style exaggeration (0-1) | 0 |
request_body.voice | string | No | The voice to use for speech generation | Rachel |
request_body.next_text | string | unknown | No | The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. | — |
request_body.stability | number | No | Voice stability (0-1) | 0.5 |
request_body.timestamps | boolean | No | Whether to return timestamps for each word in the generated speech | false |
request_body.language_code | string | unknown | No | Language code (ISO 639-1) used to enforce a language for the model. An error will be returned if language code is not supported by the model. | — |
request_body.previous_text | string | unknown | No | The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. | — |
request_body.similarity_boost | number | No | Similarity boost (0-1) | 0.75 |
request_body.apply_text_normalization | enum (auto | on | off) | No | This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. | auto |
Invocation example
Copy the request and explore its response example.
POST
/agent-api/v1/tool/executeX-Api-KeySubmit 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_elevenlabs_tts_multilingual_v2' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"request_body": {
"apply_text_normalization": "on",
"language_code": "zh",
"similarity_boost": 0.75,
"stability": 0.5,
"style": 0,
"text": "一次动火作业,稍有疏忽,就是一场火灾。",
"voice": "George"
}
}
}'Response exampleresponse.json
{
"description": "task accepted; poll the result via query_tool with this task_id",
"query_tool": "ae_get_result",
"status": "created",
"task_id": "ba88f734-80aa-4bdc-b956-d40e05d40f9e"
}Guides using this tool
See how this tool fits into real workflows
Text-to-Speech Model Comparison on One PlatformSynthesize the same script across multiple TTS models in parallel and let an AI agent compare voice, naturalness, language coverage, and emotion — run the whole shootout with one key and pick the right voice model.Chinese & Multilingual AI Voiceover (TTS): Batch Audio with AgentsTurn text into natural Chinese voiceover with an AI agent, with lively voices and multilingual support. Learn how to compare multiple TTS models, batch-generate audio in natural language, and feed it into digital-human video.




