List Text-to-Speech Models
GEThttps://api.knoxstudio.ai/v1/text-to-speech/models
Returns TTS models. Use id as model_id on convert/stream/WebSocket endpoints. See Text to Speech.
Authentication is optional (public catalog 60/min, cached 5 minutes; a token filters the list).
Request
Request Headers
| Name | Type | Required | Description |
|---|---|---|---|
| Authorization | String | No | Optional Bearer <token>. Omit for the public catalog. xi-api-key is also accepted. |
cURL Example
curl -X GET https://api.knoxstudio.ai/v1/text-to-speech/models
Response
Success Response (200)
{
"data": [
{
"id": "eleven_multilingual_v2",
"canonical_slug": "eleven_multilingual_v2",
"name": "ElevenLabs Multilingual v2",
"created": 1690848000,
"description": "Stable, lifelike narration in 29 languages. Default TTS model. Up to 10,000 characters per request.",
"chinese_description": "29 种语言的稳定拟真朗读,默认 TTS 模型,单次最多 10,000 字符。",
"max_characters": 10000,
"pricing": {
"per_thousand_characters": "0.15"
},
"architecture": {
"modality": "audio",
"input_modalities": ["text"],
"output_modalities": ["audio"],
"tokenizer": "elevenlabs"
}
}
]
}
Also listed: eleven_v3 ($0.15 / 1K, 5,000 chars), eleven_v3_conversational, eleven_flash_v2_5, eleven_flash_v2, eleven_turbo_v2_5, eleven_turbo_v2 (low-latency models $0.10 / 1K).
Response Schema
| Name | Type | Description |
|---|---|---|
| data[].id | string | Send as model_id. |
| data[].max_characters | integer | Per-request character cap. |
| data[].pricing.per_thousand_characters | string | USD per 1,000 characters. |
Error Responses
Validation uses HTTP 422:
{
"detail": [
{
"loc": ["body", "field"],
"msg": "…",
"type": "value_error"
}
]
}
Other errors use { "detail": "message" }.
| Status | When |
|---|---|
400 | WebSocket path called without Upgrade: websocket. |
401 | Missing or invalid API key. |
402 | Insufficient credits. |
403 | Token is not allowed to use this model. |
404 | Resource not found. |
422 | Validation error. |
429 | Rate limit exceeded. |
500 | Internal server error. |