curl -X POST 'https://api.elevenlabs.io/v1/flows/text-to-speech' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "webhook": {
    "type": "all"
  },
  "text": "string",
  "voice": "string",
  "output_format": "mp3_44100_128",
  "pronunciation_dictionary_locators": [
    {
      "pronunciation_dictionary_id": "string",
      "version_id": "string"
    }
  ],
  "model_id": "string",
  "language_code": "string",
  "voice_settings": {
    "stability": 0,
    "similarity_boost": 0,
    "speed": 0
  }
}'

# POST /v1/flows/text-to-speech (ElevenLabs API)
Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03

> Create Speech Generation

## Critical Gotchas
* Authentication uses the non-standard `xi-api-key` header, not `Authorization: Bearer`. Sending a Bearer token returns HTTP 401.
* Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (`--output speech.mp3`) rather than parsing it.

## cURL
curl -X POST 'https://api.elevenlabs.io/v1/flows/text-to-speech' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"webhook":{"type":"all"},"text":"string"}'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| text | body | string | Yes | The text to synthesize into speech. |
| voice | body | string | Yes | The ID of the voice to speak with. |
| model_id | body | string | Yes | The model to use for the generation. |

## Response (200 OK)
{"id":"JWr5N6X9ZTqf8jD2LmQb","status":"pending"}

---
Need an API key? Get one at https://elevenlabs.io/app/sign-up

POST

/v1/flows/text-to-speech

ElevenLabs API

Create Speech Generation

Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03 · upstream hash matched

Actions

Agents: curl -H "Accept: text/markdown" this URL
→ 215 tokens · Vary: Accept

Critical gotchas

Authentication uses the non-standard xi-api-key header, not Authorization: Bearer. Sending a Bearer token returns HTTP 401.

Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (--output speech.mp3) rather than parsing it.

cURL

curl -X POST 'https://api.elevenlabs.io/v1/flows/text-to-speech' \  -H "xi-api-key: $ELEVENLABS_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "webhook": {    "type": "all"  },  "text": "string",  "voice": "string",  "output_format": "mp3_44100_128",  "pronunciation_dictionary_locators": [    {      "pronunciation_dictionary_id": "string",      "version_id": "string"    }  ],  "model_id": "string",  "language_code": "string",  "voice_settings": {    "stability": 0,    "similarity_boost": 0,    "speed": 0  }}'

Get a free ElevenLabs API key → sponsored

Parameters

Name	In	Type	Required	Description
webhook	body	object	No	Include to send the generation's result to the workspace's configured flows webhooks once it completes or fails. The webhook payload matches the terminal response of the corresponding GET endpoint.
text	body	string	Yes	The text to synthesize into speech.
voice	body	string	Yes	The ID of the voice to speak with.
output_format	body	string	No	The audio encoding of the output, as `codec_sampleRateHz_bitrateKbps`. `mp3_44100_192` requires the Creator tier or above.
pronunciation_dictionary_locators	body	object[]	No	Pronunciation dictionaries to apply to the text, in order of precedence. Up to 3.
model_id	body	string	Yes	The model to use for the generation.
language_code	body	string	No	ISO 639-1 language code to enforce on the output. Omit to detect the language from the text.
voice_settings	body	object	No	Overrides for the voice's saved settings, applied to this generation only.

Response 200 OK

{
  "id": "JWr5N6X9ZTqf8jD2LmQb",
  "status": "pending"
}