Create Speech

POST 
https://api.knoxstudio.ai/v1/text-to-speech/:voice_id

Synthesize the full text with an ElevenLabs voice_id from Voices. A public voice such as 21m00Tcm4TlvDq8ikWAM also works. Default model eleven_multilingual_v2. Billed per character ($0.15 or $0.10 / 1K). Guide: Text to Speech.

Request

Path Parameters

Name	Type	Required	Description
voice_id	String	Yes	ElevenLabs voice ID.

Query Parameters

Name	Type	Required	Description
enable_logging	Boolean	No	Default true. false requests zero-retention mode.
optimize_streaming_latency	Integer	No	Deprecated. 0–4 latency/quality tradeoff.
output_format	String	No	Default mp3_44100_128. Format is codec_sample_rate_bitrate.

Allowed output_format values include WAV: alaw_8000, mp3_22050_32, mp3_24000_48, mp3_44100_128, mp3_44100_192, mp3_44100_32, mp3_44100_64, mp3_44100_96, opus_48000_128, opus_48000_192, opus_48000_32, opus_48000_64, opus_48000_96, pcm_16000, pcm_22050, pcm_24000, pcm_32000, pcm_44100, pcm_48000, pcm_8000, ulaw_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100, wav_48000, wav_8000.

Request Headers

Name	Type	Required	Description
Authorization	String	Yes	Bearer <token> Knox API key. xi-api-key is also accepted.
Content-Type	String	Yes	application/json.

Request Body

Name	Type	Required	Description
text	String	Yes	Text to speak. Max characters depend on model_id (5,000–40,000).
model_id	String	No	Default eleven_multilingual_v2. See GET /v1/text-to-speech/models.
language_code	String	No	ISO 639-1. Ignored by eleven_multilingual_v2.
voice_settings	Object	No	Per-request overrides: stability (0.5), similarity_boost (0.75), style (0), speed (1.0), use_speaker_boost (true).
pronunciation_dictionary_locators	List of Objects	No	Up to 3 locators with pronunciation_dictionary_id and optional version_id.
seed	Integer	No	0–4294967295. Best-effort determinism.
previous_text	String	No	Preceding text for continuity.
next_text	String	No	Following text for continuity.
previous_request_ids	List of Strings	No	Up to 3 prior request_id values. Overrides previous_text if both are sent.
next_request_ids	List of Strings	No	Up to 3 following request_id values. Overrides next_text if both are sent.
apply_text_normalization	String	No	auto (default), on, or off.
apply_language_text_normalization	Boolean	No	Extra language normalization (Japanese). Increases latency. Default false.

cURL Example

curl -X POST "https://api.knoxstudio.ai/v1/text-to-speech/21m00Tcm4TlvDq8ikWAM?output_format=mp3_44100_128" \
     -H "Authorization: Bearer $KNOXCHAT_API_KEY" \
     -H "Content-Type: application/json" \
     -o speech.mp3 \
     -d '{
  "text": "Hello from Knox. This is text to speech.",
  "model_id": "eleven_multilingual_v2"
}'

Response

Success Response (200)

The generated audio file. Content-Type follows output_format.

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.