ElevenLabs Eleven v3 API, ElevenLabs Music API: Pricing, Documentation
by ElevenLabs
ElevenLabs Eleven v3 API, developers can generate lifelike speech in multiple languages, clone voices from short audio samples, and create original music tracks. The API powers applications ranging from audiobook narration and podcast production to real-time voice assistants and multilingual content localization with human-quality audio output.
Models Version
WELCOME BONUS
Get $5 Free Credit on First Payment
No strings attached — add funds and get $5 bonus instantly
ElevenLabs Eleven v3 TTS API Documentation
https://gateway.pixazo.ai/elevenlabs-eleven-v3-tts/v1/elevenlabs-eleven-v3-tts-requestAuthentication
All requests require an API key passed via header.
| Header | Type | Required | Description |
|---|---|---|---|
| Ocp-Apim-Subscription-Key | string | Yes | Your API subscription key |
ElevenLabs Eleven v3 TTS generate request
Request Code
POST https://gateway.pixazo.ai/elevenlabs-eleven-v3-tts/v1/elevenlabs-eleven-v3-tts-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY
{
"text": "[excited] Welcome to the future of voice. [whispers] Listen closely. [laughs] This is amazing.",
"voice": "Rachel",
"stability": 0.5,
"timestamps": false,
"apply_text_normalization": "auto"
}import requests
url = "https://gateway.pixazo.ai/elevenlabs-eleven-v3-tts/v1/elevenlabs-eleven-v3-tts-request"
headers = {
"Content-Type": "application/json",
"Cache-Control": "no-cache",
"Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
"text": "[excited] Welcome to the future of voice. [whispers] Listen closely. [laughs] This is amazing.",
"voice": "Rachel",
"stability": 0.5,
"timestamps": false,
"apply_text_normalization": "auto"
}
response = requests.post(url, json=data, headers=headers)
print(response.json())const url = "https://gateway.pixazo.ai/elevenlabs-eleven-v3-tts/v1/elevenlabs-eleven-v3-tts-request";
const headers = {
"Content-Type": "application/json",
"Cache-Control": "no-cache",
"Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
"text": "[excited] Welcome to the future of voice. [whispers] Listen closely. [laughs] This is amazing.",
"voice": "Rachel",
"stability": 0.5,
"timestamps": false,
"apply_text_normalization": "auto"
};
fetch(url, {
method: "POST",
headers: headers,
body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data));curl -X POST "https://gateway.pixazo.ai/elevenlabs-eleven-v3-tts/v1/elevenlabs-eleven-v3-tts-request" \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
--data-raw '{
"text": "[excited] Welcome to the future of voice. [whispers] Listen closely. [laughs] This is amazing.",
"voice": "Rachel",
"stability": 0.5,
"timestamps": false,
"apply_text_normalization": "auto"
}'Output
{
"request_id": "elevenlabs-eleven-v3-tts_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "QUEUED",
"polling_url": "https://gateway.pixazo.ai/v2/requests/status/elevenlabs-eleven-v3-tts_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}Webhook (Optional)
Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.
X-Webhook-URL: https://your-server.com/webhook/callbackRequest Parameters - ElevenLabs Eleven v3 TTS generate request
| Parameter | Required | Type | Default | Allowed values / range | Description |
|---|---|---|---|---|---|
| text | Yes | string | — | 1–5000 characters | Text to convert to speech (1–5000 characters). Supports inline emotion tags such as [whispers], [laughs], [excited]. |
| voice | No | string | "Rachel" | Any ElevenLabs voice name or voice ID | Voice used for speech generation. Accepts a voice name or an ElevenLabs voice ID. Voices supported by Eleven v3 include: Rachel, Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily and Bill. |
| stability | No | float | 0.5 | 0.0–1.0 | Voice stability (0.0–1.0). Lower values (e.g., 0.2) produce more expressive, variable speech; higher values (e.g., 0.8) produce more consistent, steady speech. |
| timestamps | No | boolean | false | — | If true, returns an array of per-word timestamps alongside the audio output. |
| language_code | No | string | — | — | ISO 639-1 language code (e.g., "en", "es", "ja") to enforce a specific spoken language. Overrides auto-detection. |
| apply_text_normalization | No | enum | "auto" | "auto", "on", "off" | Whether to apply text normalization rules. Allowed values: auto, on, off. auto applies normalization only when beneficial; on forces it; off disables it entirely. |
Content Item Types & Limits
| Type | Max | Format / Size | Description |
|---|---|---|---|
| audio | 1 | MP3, WAV | Reference voice. |
Example Request
{
"text": "[excited] Welcome to the future of voice. [whispers] Listen closely. [laughs] This is amazing.",
"voice": "Rachel",
"stability": 0.5,
"timestamps": false,
"apply_text_normalization": "auto"
}Response
{
"request_id": "elevenlabs-eleven-v3-tts_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "QUEUED",
"polling_url": "https://gateway.pixazo.ai/v2/requests/status/elevenlabs-eleven-v3-tts_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}Request Headers
| Header | Value |
|---|---|
| Content-Type | application/json |
| Cache-Control | no-cache |
| Ocp-Apim-Subscription-Key | YOUR_API_KEY |
Response Handling
Common status codes.
| Code | Meaning |
|---|---|
| 202 | Accepted — Request queued |
| 400 | Bad Request |
| 401 | Unauthorized |
| 402 | Insufficient Balance |
| 403 | Forbidden |
| 429 | Too Many Requests |
| 500 | Internal Server Error |
Error Responses
Queue system errors and model validation errors.
Queue System Errors
// 402 — Insufficient balance
{
"error": "Insufficient Balance",
"message": "Your wallet does not have enough balance."
}// 400 — Model not found
{
"error": "Model not found",
"message": "Model 'elevenlabs-eleven-v3-tts' not found or is disabled"
}Error via Status/Webhook
{
"request_id": "elevenlabs-eleven-v3-tts_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "ERROR",
"model_id": "elevenlabs-eleven-v3-tts",
"error": "Description of the error",
"output": null
}Retrieving Results
Poll the universal status endpoint to check progress and retrieve results.
Endpoint
GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEYcURL Example
curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
"https://gateway.pixazo.ai/v2/requests/status/elevenlabs-eleven-v3-tts_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"Response (Completed)
{
"request_id": "elevenlabs-eleven-v3-tts_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "COMPLETED",
"model_id": "elevenlabs-eleven-v3-tts",
"error": null,
"output": {
"media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/elevenlabs-eleven-v3-tts_019dxxxx/output.mp3"],
"media_type": "audio/mpeg"
},
"created_at": "2026-03-31T10:00:00.000Z",
"updated_at": "2026-03-31T10:00:15.000Z",
"completed_at": "2026-03-31T10:00:15.000Z"
}Response Fields
| Field | Type | Description |
|---|---|---|
| request_id | string | Unique request identifier |
| status | string | QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR |
| model_id | string | Model that processed the request |
| error | string|null | Error message if failed |
| output.media_url | array | URLs to generated media (R2 CDN) |
| output.media_type | string | MIME type of the output |
| created_at | string | When request was created |
| completed_at | string | When request completed |
| polling_url | string | Status URL (initial response only) |
Status Values
| Status | Description |
|---|---|
| QUEUED | Request accepted, waiting to be processed |
| PROCESSING | Being processed by the model |
| COMPLETED | Done — output contains the result |
| FAILED | Failed — check error field |
| ERROR | System error — not charged |
Status Flow
QUEUED → PROCESSING → COMPLETED
→ FAILED
→ ERRORTypical Workflow
- Send a generate request to the API endpoint
- Save the
request_idfrom the response - Poll every 5-10 seconds:
GET /v2/requests/status/{request_id} - When
statusis"COMPLETED", download fromoutput.media_url
Tip: Use X-Webhook-URL header to get a callback instead of polling.
ElevenLabs Eleven v3 TTS API Pricing
Your request will cost $0.10 per 1,000 characters.
about $0.120 for a typical 200-word paragraph
equivalent to $100 per 1M characters
2. ElevenLabs Music
ElevenLabs Music API Documentation
https://gateway.pixazo.ai/elevenlabs-music/v1/elevenlabs-music-requestAuthentication
All requests require an API key passed via header.
| Header | Type | Required | Description |
|---|---|---|---|
| Ocp-Apim-Subscription-Key | string | Yes | Your API subscription key |
ElevenLabs Music generate request
Request Code
POST https://gateway.pixazo.ai/elevenlabs-music/v1/elevenlabs-music-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY
{
"prompt": "Uplifting indie folk track with acoustic guitar, soft piano, and warm harmonies",
"music_length_ms": 30000,
"force_instrumental": false,
"respect_sections_durations": true,
"output_format": "mp3_44100_128"
}import requests
url = "https://gateway.pixazo.ai/elevenlabs-music/v1/elevenlabs-music-request"
headers = {
"Content-Type": "application/json",
"Cache-Control": "no-cache",
"Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
"prompt": "Uplifting indie folk track with acoustic guitar, soft piano, and warm harmonies",
"music_length_ms": 30000,
"force_instrumental": false,
"respect_sections_durations": true,
"output_format": "mp3_44100_128"
}
response = requests.post(url, json=data, headers=headers)
print(response.json())const url = "https://gateway.pixazo.ai/elevenlabs-music/v1/elevenlabs-music-request";
const headers = {
"Content-Type": "application/json",
"Cache-Control": "no-cache",
"Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
"prompt": "Uplifting indie folk track with acoustic guitar, soft piano, and warm harmonies",
"music_length_ms": 30000,
"force_instrumental": false,
"respect_sections_durations": true,
"output_format": "mp3_44100_128"
};
fetch(url, {
method: "POST",
headers: headers,
body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data));curl -X POST "https://gateway.pixazo.ai/elevenlabs-music/v1/elevenlabs-music-request" \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
--data-raw '{
"prompt": "Uplifting indie folk track with acoustic guitar, soft piano, and warm harmonies",
"music_length_ms": 30000,
"force_instrumental": false,
"respect_sections_durations": true,
"output_format": "mp3_44100_128"
}'Output
{
"request_id": "elevenlabs-music_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "QUEUED",
"polling_url": "https://gateway.pixazo.ai/v2/requests/status/elevenlabs-music_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}Webhook (Optional)
Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.
X-Webhook-URL: https://your-server.com/webhook/callbackRequest Parameters - ElevenLabs Music generate request
| Parameter | Required | Type | Default | Allowed values / range | Description |
|---|---|---|---|---|---|
| prompt | Conditional | string | — | — | Text prompt describing the music to generate. Example: "Uplifting indie folk track with acoustic guitar, soft piano, and warm harmonies". Provide either prompt or composition_plan: the two cannot be used together, and at least one must be supplied. |
| composition_plan | Conditional | object | — | — | Structured composition plan used instead of prompt for fine-grained control. Contains positive_global_styles, negative_global_styles, and sections. Each section requires section_name (1–100 characters), positive_local_styles, negative_local_styles, duration_ms (3000–120000), and lines (max 30 lines, up to 200 characters each). When supplied, the track length is the sum of the section durations, so music_length_ms is ignored. |
| music_length_ms | No | integer | — | 3000–600000 | Length of the generated track in milliseconds (3 seconds to 10 minutes). Used only with prompt and ignored when composition_plan is supplied. If omitted, the model chooses a suitable length. |
| force_instrumental | No | boolean | false | — | If true, guarantees an instrumental track with no vocals. Applies to prompt-based generation. |
| respect_sections_durations | No | boolean | true | — | If true, enforces strict adherence to the duration_ms of each section in composition_plan; if false, the model may vary section timing. Applies only when composition_plan is supplied. |
| output_format | No | enum | "mp3_44100_128" | mp3_22050_32, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, pcm_8000, pcm_16000, pcm_22050, pcm_24000, pcm_44100, pcm_48000, ulaw_8000, alaw_8000, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192 | Audio codec, sample rate, and bitrate. |
Example Request
{
"prompt": "Uplifting indie folk track with acoustic guitar, soft piano, and warm harmonies",
"music_length_ms": 30000,
"force_instrumental": false,
"respect_sections_durations": true,
"output_format": "mp3_44100_128"
}Response
{
"request_id": "elevenlabs-music_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "QUEUED",
"polling_url": "https://gateway.pixazo.ai/v2/requests/status/elevenlabs-music_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}Request Headers
| Header | Value |
|---|---|
| Content-Type | application/json |
| Cache-Control | no-cache |
| Ocp-Apim-Subscription-Key | YOUR_API_KEY |
Response Handling
Common status codes.
| Code | Meaning |
|---|---|
| 202 | Accepted — Request queued |
| 400 | Bad Request |
| 401 | Unauthorized |
| 402 | Insufficient Balance |
| 403 | Forbidden |
| 429 | Too Many Requests |
| 500 | Internal Server Error |
Error Responses
Queue system errors and model validation errors.
Queue System Errors
// 402 — Insufficient balance
{
"error": "Insufficient Balance",
"message": "Your wallet does not have enough balance."
}// 400 — Model not found
{
"error": "Model not found",
"message": "Model 'elevenlabs-music' not found or is disabled"
}Error via Status/Webhook
{
"request_id": "elevenlabs-music_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "ERROR",
"model_id": "elevenlabs-music",
"error": "Description of the error",
"output": null
}Retrieving Results
Poll the universal status endpoint to check progress and retrieve results.
Endpoint
GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEYcURL Example
curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
"https://gateway.pixazo.ai/v2/requests/status/elevenlabs-music_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"Response (Completed)
{
"request_id": "elevenlabs-music_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"status": "COMPLETED",
"model_id": "elevenlabs-music",
"error": null,
"output": {
"media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/elevenlabs-music_019dxxxx/output.mp3"],
"media_type": "audio/mpeg"
},
"created_at": "2026-03-31T10:00:00.000Z",
"updated_at": "2026-03-31T10:00:15.000Z",
"completed_at": "2026-03-31T10:00:15.000Z"
}Response Fields
| Field | Type | Description |
|---|---|---|
| request_id | string | Unique request identifier |
| status | string | QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR |
| model_id | string | Model that processed the request |
| error | string|null | Error message if failed |
| output.media_url | array | URLs to generated media (R2 CDN) |
| output.media_type | string | MIME type of the output |
| created_at | string | When request was created |
| completed_at | string | When request completed |
| polling_url | string | Status URL (initial response only) |
Status Values
| Status | Description |
|---|---|
| QUEUED | Request accepted, waiting to be processed |
| PROCESSING | Being processed by the model |
| COMPLETED | Done — output contains the result |
| FAILED | Failed — check error field |
| ERROR | System error — not charged |
Status Flow
QUEUED → PROCESSING → COMPLETED
→ FAILED
→ ERRORTypical Workflow
- Send a generate request to the API endpoint
- Save the
request_idfrom the response - Poll every 5-10 seconds:
GET /v2/requests/status/{request_id} - When
statusis"COMPLETED", download fromoutput.media_url
Tip: Use X-Webhook-URL header to get a callback instead of polling.
ElevenLabs Music API Pricing
Your request will cost $0.80 per minute of generated music.
billed in 1-minute increments, rounded up