Text-to-Speech WebSocket voice settings

Reference for provider-specific voice configuration sent in the handshake frame for Telnyx Text-to-Speech WebSocket streaming, including speed and style.

voice_settings is an object sent in the handshake frame to configure provider-specific parameters:

{
  "text": " ",
  "voice_settings": {
    "voice_speed": 1.2
  }
}

Telnyx Ultra

Telnyx Ultra is REST-only — not available over WebSocket. These settings apply to the REST API.

Parameter	Type	Default	Description
voice_speed	float	1.0	Speech rate. Values > 1 are faster.
language_boost	string	—	Target language
volume	float	—	Volume level
emotion	string	—	Emotion: neutral, happy, sad, angry, fearful, disgusted, surprised

Telnyx Qwen3TTS

Parameter	Type	Default	Description
language_boost	string	"Auto"	Target language. Accepted: Auto, English, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish, or ISO codes (en, zh, etc.)

Azure Speech

Parameter	Type	Default	Description
language_code	string	"en-US"	Language code
text_type	string	"text"	Input type: text or ssml
effect	string	—	Audio effect: eq_car or eq_telecomhp8k
gender	string	—	Voice gender filter: Male or Female

AWS Polly

Parameter	Type	Default	Description
language_code	string	—	BCP-47 language code
output_format	string	—	Audio format override
engine	string	"standard"	Polly engine: standard, neural, generative, long-form
text_type	string	"text"	Input type: text or ssml
lexicon_names	array	—	Pronunciation lexicon names

Minimax

Parameter	Type	Default	Description
speed	float	—	Speech rate
vol	float	—	Volume
pitch	integer	—	Pitch adjustment
language_boost	string	—	Language emphasis

Inworld

Parameter	Type	Default	Description
language_code	string	—	Language code
delivery_mode	string	—	STABLE, BALANCED, or CREATIVE. Only supported by inworld-tts-2.

Fish Audio

Parameter	Type	Default	Description
format	string	"pcm"	mp3, wav, pcm, opus
sample_rate	integer	24000	Valid values depend on format: pcm/wav — 8000, 16000, 24000, 32000, 44100; mp3 — 32000, 44100; opus — 48000

Soniox

Parameter	Type	Default	Description
language	string	en	Two-letter ISO 639-1 code of the text.
speed	float	1.0	Speaking rate, 0.7 to 1.3.
reduce_silence	boolean	false	Shortens the pauses between words.

Output format and sample rate come from the audio_format and sample_rate query parameters — see Soniox WebSocket provider.