Azure speech-to-text now available via Telnyx

Telnyx is expanding Speech-to-Text engine options to give developers more flexibility for building low-latency, multilingual transcription workflows. Alongside existing support for Telnyx Speech-to-Text, Google Speech-to-Text and Deepgram, you can now use Azure Speech-to-Text through the Telnyx Speech-to-Text API, Voice API and Voice AI Agents.

This expanded lineup makes Telnyx the easiest way to build and scale multilingual speech recognition without locking you into a single provider.

What’s new

1. Azure Speech-to-Text support via Telnyx Speech-to-Text.
2. Expanded engine selection, including:
   • Telnyx Speech-to-Text (Whisper)
   • Google Speech-to-Text
   • Azure Speech-to-Text
   • Deepgram Nova 2
   • Deepgram Nova 3
   • Deepgram Flux

Key benefits

Azure Speech-to-Text is an enterprise-grade option for reliable real-time streaming, broad language/locale support, and consistent performance at scale.

Different transcription engines excel in different areas such as languages, acoustic conditions, latency needs, or accuracy tradeoffs. With flexible engine selection through Telnyx, developers can:

• Build low-latency transcription experiences for real-time workflows
• Support 100+ languages and dialects for global products
• Switch engines quickly as requirements evolve without rebuilding pipelines

Getting started

1. Sign in to your Telnyx Mission Control Portal
2. Generate an API key for Speech-to-Text
3. Choose your Azure as your transcription engine
4. Stream audio and receive transcripts in real time

or

1. Navigate to the AI Assistants section
2. Select Azure as as your transcription engine in the voice playground section
3. Build your AI agent in minutes

Read our developer documents to learn more and see our pricing.