voice_settings configures provider-specific parameters in the request body:
Telnyx Ultra
| Parameter | Type | Range | Description |
|---|---|---|---|
emotion | string | — | Emotion: neutral, happy, sad, angry, etc. |
speed | float | 0.5–2.0 | Speech rate (1.0 = normal) |
volume | float | 0.0–2.0 | Volume level (1.0 = normal) |
language request parameter.
Telnyx Natural / NaturalHD
| Parameter | Type | Default | Description |
|---|---|---|---|
voice_speed | float | 1.0 | Speech rate |
embedding_scale | float | — | Voice embedding intensity |
diffusion_steps | integer | — | Quality/latency tradeoff |
phonemizer | string | — | Phonemizer backend |
response_format | string | — | Audio format override (pcm, wav) |
Telnyx Qwen3TTS
| Parameter | Type | Default | Description |
|---|---|---|---|
language_boost | string | "Auto" | Target language: Auto, English, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish (or ISO codes) |
force_xvector | boolean | false | Force x-vector voice embedding |
AWS Polly
| Parameter | Type | Default | Description |
|---|---|---|---|
engine | string | "standard" | standard, neural, generative, long-form |
language_code | string | — | BCP-47 language code |
text_type | string | "text" | text or ssml |
output_format | string | — | Audio format |
sample_rate | string | — | Sample rate |
lexicon_names | array | — | Pronunciation lexicon names |
Azure Speech
| Parameter | Type | Default | Description |
|---|---|---|---|
language_code | string | "en-US" | Language |
output_format | string | "audio-24khz-160kbitrate-mono-mp3" | Azure output format |
text_type | string | "text" | text or ssml |
effect | string | — | eq_car or eq_telecomhp8k |
gender | string | — | Male or Female |
ElevenLabs
| Parameter | Type | Description |
|---|---|---|
language_code | string | Language |
voice_settings | object | Nested settings (stability, similarity_boost, style, use_speaker_boost) |
Minimax
| Parameter | Type | Description |
|---|---|---|
speed | float | Speech rate |
vol | float | Volume |
pitch | integer | Pitch |
language_boost | string | Language emphasis |
Rime
| Parameter | Type | Default | Description |
|---|---|---|---|
voice_speed | float | 1.0 | Speech rate |
response_format | string | "mp3" | Audio format |
sampling_rate | integer | 24000 | Sample rate (Hz) |
Resemble
| Parameter | Type | Default | Description |
|---|---|---|---|
precision | string | "PCM_32" | PCM_16, PCM_24, PCM_32, MULAW |
sample_rate | string | "48000" (mp3) / "16000" (wav) | Sample rate |
format | string | "mp3" | wav or mp3 |
Inworld
| Parameter | Type | Default | Description |
|---|---|---|---|
encoding | string | "MP3" (REST) | MP3 or LINEAR16 |
sample_rate | integer | 24000 | Sample rate (Hz) |
language_code | string | — | Language |