Model ID

elevenlabs-tts-v3

ElevenLabs TTS v3 API Usage Guide

Overview

Key Features:

10 Preset Voices: Curated selection of professional voices for various use cases
Advanced Voice Control: Fine-tune stability, similarity, style, and speed for personalized output
Multi-Language Support: Native support for 29+ languages including English, Spanish, French, German, Polish, and more
High-Quality Audio: Multiple output formats (MP3, PCM) with adjustable sample rates and bitrates
Speaker Boost: Enhanced voice clarity and presence
Deterministic Generation: Set seed for reproducible results

Authentication

All API requests require authentication using an API key. Include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Submit Video Generation Request

Base URL

https://console.gmicloud.ai

Endpoint

POST /api/v1/ie/requestqueue/apikey/requests

Request Format

curl -X POST "https://console.gmicloud.ai/api/v1/ie/requestqueue/apikey/requests" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "elevenlabs-tts-v3",
    "payload": {
      "text": "Welcome to the world of natural-sounding speech synthesis.",
      "voice_id": "21m00Tcm4TlvDq8ikWAM",
      "stability": 0.5,
      "similarity_boost": 0.75,
      "style": 0.0,
      "speed": 1.0,
      "use_speaker_boost": true,
      "output_format": "mp3_44100_128",
      "seed": 0,
      "apply_text_normalization": "auto"
    }
  }'

Request Parameters

Parameter	Type	Required	Description	Default	Constraints
`text`	string	Yes	Text content to be converted to speech.	-	Required
`voice_id`	string	No	Voice ID for speech synthesis. Each voice has unique characteristics and accents.	”21m00Tcm4TlvDq8ikWAM”	See Voice ID List below
`stability`	enum	No	Voice stability mode for eleven_v3 model.	0.5	Options: 0.0 (Creative), 0.5 (Natural), 1.0 (Robust)
`similarity_boost`	float	No	Similarity boost enhances the resemblance to the original voice. Higher values make the voice closer to the original.	0.75	Range: 0.0–1.0, Step: 0.05
`style`	float	No	Style exaggeration. Higher values amplify the voice’s characteristic style.	0.0	Range: 0.0–1.0, Step: 0.05
`speed`	float	No	Speech speed multiplier. 1.0 is normal speed.	1.0	Range: 0.5–2.0, Step: 0.1
`use_speaker_boost`	boolean	No	Enable speaker boost for enhanced voice clarity and presence.	true	Optional
`output_format`	string	No	Output audio format. MP3 formats use lossy compression, PCM formats are uncompressed. Higher bitrates and sample rates require higher subscription tiers.	”mp3_44100_128”	See Output Format Options below
`seed`	integer	No	Random seed for deterministic generation. Same seed with same parameters produces same result.	0	Range: 0–4294967295
`apply_text_normalization`	string	No	Text normalization mode. Auto lets the system decide, On always normalizes (e.g., spelling out numbers), Off skips normalization.	”auto”	Options: “auto”, “on”, “off”

Available Voice IDs

Voice ID	Display Name	Use Case
`21m00Tcm4TlvDq8ikWAM`	Rachel	Conversational, Narration
`29vD33N1CtxCmqQRPOHJ`	Drew	News, Professional
`2EiwWnXFnvU5JabPnv8n`	Clyde	Character, Animation
`5Q0t7uMcjvnagumLfvZi`	Paul	News, Broadcasting
`9BWtsMINqrJLrRacOk9x`	Aria	Educational, Tutorial
`AZnzlk1XvdvUeBnXmlld`	Domi	Narration, Audiobooks
`CYw3kZ02Hs0563khs1Fj`	Dave	British Accent, Professional
`CwhRBWXzGAHq8TQ4Fs17`	Roger	Conversational, Casual
`D38z5RcWu1voky8WS1ja`	Fin	Irish Character, Storytelling
`EXAVITQu4vr4xnSDxMaL`	Sarah	Entertainment, Upbeat

Output Format Options

Format Value	Display Name	Description
`mp3_22050_32`	MP3 22.05kHz 32kbps	Low quality, smallest file size
`mp3_44100_32`	MP3 44.1kHz 32kbps	Standard quality, low bitrate
`mp3_44100_64`	MP3 44.1kHz 64kbps	Standard quality, medium bitrate
`mp3_44100_96`	MP3 44.1kHz 96kbps	Good quality, medium bitrate
`mp3_44100_128`	MP3 44.1kHz 128kbps	High quality (default)
`mp3_44100_192`	MP3 44.1kHz 192kbps	Very high quality
`pcm_16000`	PCM 16kHz	Uncompressed, 16kHz
`pcm_22050`	PCM 22.05kHz	Uncompressed, 22.05kHzl
`pcm_24000`	PCM 24kHz	Uncompressed, 24kHz
`pcm_44100`	PCM 44.1kHz	Uncompressed, CD quality
`pcm_48000`	PCM 48kHz	Uncompressed, studio quality

Response

{
  "request_id": "7eaa77fc-bc67-4021-9f1b-96b3fd832314",
  "model": "elevenlabs-tts-v3",
  "status": "queued",
  "created_at": 1761763441,
  "updated_at": 1761763441,
  "queued_at": 1761763441
}

Check Request Status

Endpoint

GET /api/v1/ie/requestqueue/apikey/requests/{request_id}

Example

curl -X GET "https://console.gmicloud.ai/api/v1/ie/requestqueue/apikey/requests/7eaa77fc-bc67-4021-9f1b-96b3fd832314" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

{
  "request_id": "7eaa77fc-bc67-4021-9f1b-96b3fd832314",
  "model": "elevenlabs-tts-v3",
  "status": "success",
  "payload": {
    "apply_text_normalization": "auto",
    "output_format": "mp3_44100_128",
    "seed": 0,
    "similarity_boost": 0.75,
    "speed": 1,
    "stability": 0.5,
    "style": 0,
    "text": "Welcome to the world of natural-sounding speech synthesis.",
    "use_speaker_boost": true,
    "voice_id": "21m00Tcm4TlvDq8ikWAM"
  },
  "outcome": {
    "audio_url": "https://storage.googleapis.com/.../your_tts_result.mp3",
    "media": [
        {
            "type": "audio",
            "url": "https://storage.googleapis.com/.../your_tts_result.mp3"
        }
    ],
    "status": "audio_generated_successfully"
  },
  "created_at": 1761763441,
  "updated_at": 1761763451,
  "queued_at": 1761763441
}

Request Status Values

Status	Description
`queued`	Request is waiting to be processed
`processing`	Video generation is in progress
`success`	Video generation completed successfully
`failed`	Video generation failed
`cancelled`	Request was cancelled

List Your Requests

Endpoint

GET api/v1/ie/requestqueue/apikey/requests?model_id=elevenlabs-tts-v3

Example

curl -X GET "https://console.gmicloud.ai/api/v1/ie/requestqueue/apikey/requests?model_id=elevenlabs-tts-v3" \
  -H "Authorization: Bearer YOUR_API_KEY"

Get Model Information

Endpoint

GET /api/v1/ie/requestqueue/apikey/models/elevenlabs-tts-v3

Example

curl -X GET "https://api.example.com/api/v1/apikey/models/elevenlabs-tts-v3" \
  -H "Authorization: Bearer YOUR_API_KEY"

List Available Models

Endpoint

GET /api/v1/apikey/models

Example

curl -X GET "https://api.example.com/api/v1/apikey/models" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

{
    "model_ids": [
        "elevenlabs-tts-v3",
        "other-model-1",
        "other-model-2"
    ]
}

Audio Specifications

Sample Rates: 16 kHz, 22.05 kHz, 24 kHz, 44.1 kHz, 48 kHz
Formats: MP3 (lossy compression), PCM (uncompressed)
Bitrates (MP3): 32 kbps, 64 kbps, 96 kbps, 128 kbps, 192 kbps
Output: Downloadable via signed URL

Example Use Cases

Basic TTS (Minimal Required Parameters)

curl -X POST "https://console.gmicloud.ai/api/v1/ie/requestqueue/apikey/requests" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "elevenlabs-tts-v3",
    "payload": {
      "text": "Welcome to the future of speech synthesis with ElevenLabs.",
      "voice_id": "21m00Tcm4TlvDq8ikWAM"
    }
  }'

Advanced TTS (All Parameters)

curl -X POST "https://console.gmicloud.ai/api/v1/ie/requestqueue/apikey/requests" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "elevenlabs-tts-v3",
    "payload": {
      "text": "This is a comprehensive example showcasing all available parameters for professional-grade speech synthesis with full voice control.",
      "voice_id": "29vD33N1CtxCmqQRPOHJ",
      "stability": 1.0,
      "similarity_boost": 0.8,
      "style": 0.2,
      "speed": 1.1,
      "use_speaker_boost": true,
      "output_format": "mp3_44100_192",
      "seed": 12345,
      "apply_text_normalization": "on"
    }
  }'

Documentation Index

​ElevenLabs TTS v3 API Usage Guide

​Overview

​Key Features:

​Authentication

​Submit Video Generation Request

​Base URL

​Endpoint

​Request Format

​Request Parameters

​Available Voice IDs

​Output Format Options

​Response

​Check Request Status

​Endpoint

​Example

​Response

​Request Status Values

​List Your Requests

​Endpoint

​Example

​Get Model Information

​Endpoint

​Example

​List Available Models

​Endpoint

​Example

​Response

​Audio Specifications

​Example Use Cases

​Basic TTS (Minimal Required Parameters)

​Advanced TTS (All Parameters)

ElevenLabs TTS v3 API Usage Guide

Overview

Key Features:

Authentication

Submit Video Generation Request

Base URL

Endpoint

Request Format

Request Parameters

Available Voice IDs

Output Format Options

Response

Check Request Status

Endpoint

Example

Response

Request Status Values

List Your Requests

Endpoint

Example

Get Model Information

Endpoint

Example

List Available Models

Endpoint

Example

Response

Audio Specifications

Example Use Cases

Basic TTS (Minimal Required Parameters)

Advanced TTS (All Parameters)