Check out our upcoming events and meetups! View events →
WebSocket Streaming
Generate speech from text
Generate synthesized speech audio from text input. Returns audio in the requested format (binary audio stream, base64-encoded JSON, or an audio URL for later retrieval).
Authentication is provided via the standard Authorization: Bearer <API_KEY> header.
The voice parameter provides a convenient shorthand to specify provider, model, and voice in a single string (e.g. telnyx.NaturalHD.Alloy or Telnyx.Ultra.<voice_id>). Alternatively, specify provider explicitly along with provider-specific parameters.
Supported providers: aws, telnyx, azure, elevenlabs, minimax, rime, resemble, xai.
The Telnyx Ultra model supports 44 languages with emotion control, speed adjustment, and volume control. Use the telnyx provider-specific parameters to configure these features.
POST
/
text-to-speech
JavaScript
import Telnyx from 'telnyx';
const client = new Telnyx({
apiKey: process.env['TELNYX_API_KEY'], // This is the default and can be omitted
});
const response = await client.textToSpeech.generate();
console.log(response.base64_audio);"<string>"Documentation Index
Fetch the complete documentation index at: https://developers.telnyx.com/llms.txt
Use this file to discover all available pages before exploring further.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
Request body for generating speech from text.
Voice identifier in the format provider.model_id.voice_id or provider.voice_id. Examples: telnyx.NaturalHD.Alloy, Telnyx.Ultra.<voice_id>, azure.en-US-AvaMultilingualNeural, aws.Polly.Generative.Lucia. When provided, provider, model_id, and voice_id are extracted automatically and take precedence over individual parameters.
The text to convert to speech.
TTS provider. Required unless voice is provided.
Available options:
aws, telnyx, azure, elevenlabs, minimax, rime, resemble, xai Language code (e.g. en-US). Usage varies by provider.
Text type. Use ssml for SSML-formatted input (supported by AWS and Azure).
Available options:
text, ssml Determines the response format. binary_output returns raw audio bytes, base64_output returns base64-encoded audio in JSON.
Available options:
binary_output, base64_output When true, bypass the audio cache and generate fresh audio.
Provider-specific voice settings. Contents vary by provider — see provider-specific parameter objects below.
AWS Polly provider-specific parameters.
Show child attributes
Show child attributes
Telnyx provider-specific parameters. Use voice_speed and temperature for Natural and NaturalHD models. For the Ultra model, use voice_speed, volume, and emotion.
Show child attributes
Show child attributes
Azure Cognitive Services provider-specific parameters.
Show child attributes
Show child attributes
ElevenLabs provider-specific parameters.
Show child attributes
Show child attributes
Minimax provider-specific parameters.
Show child attributes
Show child attributes
Rime provider-specific parameters.
Show child attributes
Show child attributes
Resemble AI provider-specific parameters.
Show child attributes
Show child attributes
xAI provider-specific parameters.
Show child attributes
Show child attributes
Response
Speech generated successfully. The response format depends on the output_type parameter:
binary_output(default): Returns raw audio bytes with the appropriateContent-Typeheader (e.g.audio/mpeg).base64_output: Returns a JSON object withbase64_audiofield.
Raw audio bytes. Returned when output_type is binary_output (default).
Was this page helpful?
⌘I
JavaScript
import Telnyx from 'telnyx';
const client = new Telnyx({
apiKey: process.env['TELNYX_API_KEY'], // This is the default and can be omitted
});
const response = await client.textToSpeech.generate();
console.log(response.base64_audio);"<string>"Assistant
Responses are generated using AI and may contain mistakes.