Real-time Text-to-Speech API

Access leading TTS providers, Telnyx-hosted models, and custom voices through one platform. Compare voices, switch models, and manage speech generation without rebuilding provider-by-provider integrations.

CiscoOpenAITalkdeskAmerican Red CrossZillowMicrosoftCosmoIBMState of IowaCiscoOpenAITalkdeskAmerican Red CrossZillowMicrosoftCosmoIBMState of Iowa
TEXT-TO-SPEECH DEMO

Test Text-to-Speech API voices

Enter text, choose a voice, adjust speed, and hear Telnyx text-to-speech output across models in the same workflow.

Loading...
FEATURES

Production-ready text-to-speech APIs

Use one TTS API for real-time voice synthesis, model choice, streaming, in-call playback, custom voices, dubbing, and speech controls.

  • 1,300+ voices

    Access voices across Telnyx, partner, and custom models without rebuilding around each provider.

  • REST and in-call playback

    Generate audio through REST, stream speech through WebSocket, or play TTS directly in Voice API and TeXML call flows.

  • Streaming audio

    Send text and receive audio chunks for live experiences where agents, IVRs, and apps need to respond in real time.

  • Custom voice creation and dubbing

    Design synthetic voices, clone from reference audio, or support dubbing workflows with custom voices in production.

  • OpenAI SDK compatibility

    Use the REST TTS API with OpenAI-compatible client patterns when that is the fastest path for your team.

  • Model switching

    Change supported voices through configuration instead of rebuilding the application around a new provider.

  • Pronunciation control

    Use pronunciation dictionaries and supported voice settings to tune how product names, customer names, and domain terms are spoken.

TTS PROVIDERS

One API, every supported TTS provider

Route across Telnyx-hosted voices, partner models, and custom voices through a single API. Each provider keeps its own strengths in voice, language, and latency.

Keep every TTS option open with one API

  • One TTS API for every voice strategy

    Access Telnyx voices, provider models, and custom voices through one integration, instead of wiring every TTS vendor into your app separately.

  • Speech built for live voice workflows

    Use TTS in Voice API, TeXML, IVRs, AI agents, and real-time call flows, not just as a standalone audio file generator.

  • Change voices as your requirements change

    Tune for latency, accent quality, language coverage, voice style, and cost without rebuilding around a new provider each time the TTS market shifts.

HOW IT WORKS

Call the TTS API and receive audio

Send text with a voice ID, then receive generated speech over REST, WebSocket streaming, or a live call flow.

curl --request POST \
  --url https://api.telnyx.com/v1/text-to-speech \
  --header "Authorization: Bearer $TELNYX_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "text": "Your order is ready for pickup.",
    "voice": "Telnyx.NaturalHD.astra"
  }' --output speech.mp3
PRICING

How much does the Telnyx TTS API cost?

Telnyx TTS starts at $3 per 1 million characters. Pricing varies by model, with volume discounts available for larger deployments.

$3.00Starting cost per 1 million characters
RELATED PRODUCTS

Use Text-to-Speech across your voice AI stack

Text-to-speech is most useful when it connects to the call, agent, and transcription products around it.

Sign up and start building.

From first call to global deployment, Telnyx gives you the stack, scale, and support to launch real-time conversational AI with confidence.

Sign up for Telnyx Text-to-Speech

FAQ

A text-to-speech API gateway gives developers one API surface for multiple TTS engines, voices, and delivery paths. Telnyx acts as that gateway for Telnyx voices, supported provider models, custom voices, REST generation, WebSocket streaming, and in-call playback.

A text-to-speech API gateway gives developers one API surface for multiple TTS engines, voices, and delivery paths. Telnyx acts as that gateway for Telnyx voices, supported provider models, custom voices, REST generation, WebSocket streaming, and in-call playback.