Bayan

Voice format: Telnyx.Bayan.<speaker> Arabic voice model, 113 speakers across 13 dialects (Modern Standard Arabic plus Egyptian, Emirati, Saudi, Jordanian, Iraqi, Lebanese, Syrian, Palestinian, Kuwaiti, Bahraini, Qatari, and Omani), plus a set of English speakers. Native audio is 16kHz.

Voice Samples

Voice	Dialect	Gender
`Telnyx.Bayan.Ahmed`	Egyptian	Male
`Telnyx.Bayan.Alia`	Emirati	Female
`Telnyx.Bayan.Lana`	Jordanian	Female
`Telnyx.Bayan.Hind`	Qatari	Female

Browse the full 113-speaker catalogue via the Voices API.

Cloned Voices

Bayan also synthesizes organization-scoped voice clones: Telnyx.Bayan.<clone_id>. Create one with POST /v2/voice_clones/from_upload and model_id: "Bayan". See Voice Clone API parameters.

WebSocket

Query Parameters

wss://api.telnyx.com/v2/text-to-speech/speech?voice=Telnyx.Bayan.Ahmed

Parameter	Type	Default	Description
`audio_format`	string	raw PCM	`mp3`, `linear16`, `wav`. Without it, audio is raw 16-bit LE mono PCM.
`sample_rate`	integer	`16000`	`16000` (native). `8000`, `22050`, and `24000` are resampled and need `linear16`.

Voice Settings

Field	Type	Default	Description
`voice_speed`	float	`1.0`	Speech rate, `0.5` to `2.0`.

{
  "text": " ",
  "voice_settings": {
    "voice_speed": 1.1
  }
}

The same settings apply to Bayan voice clones (Telnyx.Bayan.<clone_id>).

REST API

Fields

Field	Type	Default	Description
`language`	string	Speaker’s dialect	Language/dialect hint.
`voice_speed`	float	`1.0`	Speech rate, `0.5` to `2.0`.
`response_format`	string	`wav`	`pcm`, `wav`, `mp3`. With `output_type: "base64_output"`, the default is raw PCM.
`sampling_rate`	integer	`16000`	`16000` (native). `8000`, `22050`, and `24000` are resampled and need `response_format: "pcm"`.
`output_type`	string	`binary_output`	`binary_output`, `base64_output`, or `audio_id`.

Response

Default (binary_output): a 16kHz signed 16-bit LE mono WAV. Set response_format to pcm for raw PCM or mp3 for MP3. With output_type: "base64_output": JSON with base64-encoded audio. With output_type: "audio_id": JSON with an audio_url for deferred retrieval.

sampling_rate/sample_rate values other than 8000, 16000, 22050, and 24000 are rejected with a 422 error. A non-native rate with non-PCM output is also rejected with 422.

WebSocket Streaming

REST API

Providers

Other

API Reference

For AI Agents

Voice Samples

Cloned Voices

WebSocket

Query Parameters

Voice Settings

REST API

Fields

Response

​Voice Samples

​Cloned Voices

​WebSocket

​Query Parameters

​Voice Settings

​REST API

​Fields

​Response

Voice Samples

Cloned Voices

WebSocket

Query Parameters

Voice Settings

REST API

Fields

Response