Sign in
Call Commands

Speak text

Convert text to speech and play it back on the call. If multiple speak text commands are issued consecutively, the audio files will be placed in a queue awaiting playback.

Expected Webhooks:

  • call.speak.started
  • call.speak.ended
post/calls/{call_control_id}/actions/speak

Path parameters

call_control_idstring required

Unique identifier and token for controlling the call

Request body

payloadstring required

The text or SSML to be converted into speech. There is a 3,000 character limit.

payload_type'text' | 'ssml'

The type of the provided payload. The payload can either be plain text, or Speech Synthesis Markup Language (SSML).

service_level'basic' | 'premium'

This parameter impacts speech quality, language options and payload types. When using basic, only the en-US language and payload type text are allowed.

stopstring

When specified, it stops the current audio being played. Specify current to stop the current audio being played, and to play the next file in the queue. Specify all to stop the current audio file being played and to also clear all audio files from the queue.

voicestring required

Specifies the voice used in speech synthesis.

  • Define voices using the format <Provider>.<Model>.<VoiceId>. Specifying only the provider will give default values for voice_id and model_id.

Supported Providers:

  • AWS: Use AWS.Polly.<VoiceId> (e.g., AWS.Polly.Joanna). For neural voices, which provide more realistic, human-like speech, append -Neural to the VoiceId (e.g., AWS.Polly.Joanna-Neural). Check the available voices for compatibility.
  • Azure: Use Azure.<VoiceId> (e.g., Azure.en-CA-ClaraNeural, Azure.en-US-BrianMultilingualNeural, Azure.en-US-Ava:DragonHDLatestNeural). For a complete list of voices, go to Azure Voice Gallery. Use voice_settings to configure custom deployments, regions, or API keys.
  • ElevenLabs: Use ElevenLabs.<ModelId>.<VoiceId> (e.g., ElevenLabs.eleven_multilingual_v2.21m00Tcm4TlvDq8ikWAM). The ModelId part is optional. To use ElevenLabs, you must provide your ElevenLabs API key as an integration identifier secret in "voice_settings": {"api_key_ref": "<secret_identifier>"}. See integration secrets documentation for details. Check available voices.
  • Telnyx: Use Telnyx.<model_id>.<voice_id> (e.g., Telnyx.KokoroTTS.af). Use voice_settings to configure voice_speed and other synthesis parameters. Bayan provides Arabic (multiple dialects) and English voices (e.g., Telnyx.Bayan.Ahmed, Telnyx.Bayan.Amanda). Sukhan provides Urdu voices (e.g., Telnyx.Sukhan.urdu-professor); voice_speed is not supported.
  • Minimax: Use Minimax.<ModelId>.<VoiceId> (e.g., Minimax.speech-02-hd.Wise_Woman). Supported models: speech-02-turbo, speech-02-hd, speech-2.6-turbo, speech-2.8-turbo. Use voice_settings to configure speed, volume, pitch, and language_boost.
  • Resemble: Use Resemble.Turbo.<voice_id> (e.g., Resemble.Turbo.my_voice). Only Turbo model is supported. Use voice_settings to configure precision, sample_rate, and format.
  • Inworld: Use Inworld.<ModelId>.<VoiceId> (e.g., Inworld.Mini.Loretta, Inworld.Max.Oliver, Inworld.TTS2.Loretta). Supported models: Mini, Max, TTS2. Use voice_settings to configure delivery_mode (STABLE, BALANCED, CREATIVE), supported by TTS2 only.
  • Fish Audio: Use FishAudio.<ModelId>.<VoiceId> (e.g., FishAudio.s2.1-pro.<reference_id>). Supported models: s2.1-pro, s2-pro, s1. VoiceId is a Fish Voice-Library reference ID.
  • Soniox: Use Soniox.<ModelId>.<VoiceId> (e.g., Soniox.tts-rt-v2.Emma). Supported model: tts-rt-v2. Browse the catalog via the Voices API. Every voice speaks all supported languages; set language to the two-letter ISO 639-1 code of the text, for example it. SSML is not supported. Use voice_settings to configure speed (0.7 to 1.3) and reduce_silence.
  • xAI: Use xAI.<VoiceId> (e.g., xAI.eve). Available voices: eve, ara, rex, sal, leo.
  • Humain: Use Humain.<VoiceId> (e.g., Humain.sara-ar). Available voices: sara-en, abdulaziz-en, sara-ar, abdulaziz-ar, nourah-ar, abdullah-ar. Native Arabic (Saudi dialect) and English voices only — no ModelId segment.

For service_level basic, you may define the gender of the speaker (male or female).

language'arb' | 'cmn-CN' | 'cy-GB' | 'da-DK' | 'de-DE' | 'en-AU' | 'en-GB' | 'en-GB-WLS' | 'en-IN' | 'en-US' | 'es-ES' | 'es-MX' | 'es-US' | 'fr-CA' | 'fr-FR' | 'hi-IN' | 'is-IS' | 'it-IT' | 'ja-JP' | 'ko-KR' | 'nb-NO' | 'nl-NL' | 'pl-PL' | 'pt-BR' | 'pt-PT' | 'ro-RO' | 'ru-RU' | 'sv-SE' | 'tr-TR'

The language you want spoken. This parameter is ignored when a Polly.* voice is specified.

client_statestring

Use this field to add state to every subsequent webhook. It must be a valid Base-64 encoded string.

command_idstring

Use this field to avoid duplicate commands. Telnyx will ignore any command with the same command_id for the same call_control_id.

target_legs'self' | 'opposite' | 'both'

Specifies which legs of the call should receive the spoken audio.

Example request

{
  "payload": "Say this on the call",
  "payload_type": "text",
  "service_level": "basic",
  "stop": "current",
  "voice": "female",
  "language": "arb",
  "client_state": "aGF2ZSBhIG5pY2UgZGF5ID1d",
  "command_id": "891510ac-f3e4-11e8-af5b-de00688a4901"
}

Response

Successful response upon making a call control command.

Example response

{
  "data": {
    "result": "ok"
  }
}

Changes

Changed in 4 of the 99 revisions of this API.83

  • d8b8159753ee2See the full diff
    • ○

      added soniox discriminator mapping keys to the request property

      request-property-discriminator-mapping-added

    • ○

      added to the request property oneOf list

      request-property-one-of-added

  • a6a61a29ecdd11See the full diff
    • ▲

      removed from the request property oneOf list

      request-property-one-of-removed

    • ○

      removed rime discriminator mapping keys from the request property

      request-property-discriminator-mapping-deleted

    This revision also has 34 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

  • 1571b0380bd73See the full diff
    • ▲

      the response's body type changed from object to no type for status

      response-body-type-changed

    • ▲

      the / response's property type changed from object to no type for status

      response-property-type-changed

    • ▲

      the // response's property type changed from integer to string, and format from int32 to integer for status

      response-property-type-changed

    This revision also has 64 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

  • 8f5f4e5379944See the full diff
    • ▲

      the response's body type changed from no type to object for status

      response-body-type-changed

    • ▲

      the / response's property type changed from no type to object for status

      response-property-type-changed

    • ▲

      the // response's property type changed from string to integer, and format from integer to int32 for status

      response-property-type-changed

    • ▲

      the /// response's property format changed from json-pointer to no format for status

      response-property-type-changed

    This revision also has 41 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

Of the 99 revisions, 1 has no diff computed.