Telnyx Speech-to-Text
Speech-to-text API routing audio across multiple STT engines through one Telnyx integration.
- Tool type
- Speech-to-text API with multi-engine routing
- Made for
- Developers and enterprise voice teams
- Runs on
- Telnyx API (server-side access)
- Called from developer applications over the Telnyx API; transcription runs on Telnyx infrastructure co-located with telephony.
What it does
Telnyx Speech-to-Text is a speech recognition API that turns live or recorded audio into text. Its STT Router exposes several speech engines behind one Telnyx integration, including Telnyx's own engine built on Whisper Large-V3-Turbo, Deepgram Nova 2, Nova 3 and Flux, Google, Azure, Speechmatics and AssemblyAI. The output is real-time transcription for voice agents, captions and call analytics.
Teams use it for conversational AI, customer support bots and live captions, choosing an engine per request based on accuracy, language coverage, cost or latency. Transcription runs where calls terminate, which the product page says avoids extra network hops. Switching engines is a configuration change rather than a code change.
It suits developers and enterprises building voice applications that want several engines without separate vendor relationships. Access is through the Telnyx API with an account and API key. Language coverage varies by engine: for example, Nova 3 supports 20 languages and AssemblyAI 19.
What it can do
- Routes speech-to-text requests across multiple STT engines through one API
- Supports 100+ languages across the engines available in STT Router
- Offers real-time streaming transcription for voice agents and live captions
- Enables switching STT engines via configuration rather than code changes
- Provides automatic language detection on some engines
- Runs transcription co-located with telephony infrastructure
Works with
- Telnyx Voice API and telephony network
Before you choose
- Language support varies by engine; check the chosen engine's language count before deployment.
- Pricing beyond the stated per-minute starting rate is not detailed on the STT page; confirm on the pricing page.
- Engine-specific behavior (turn detection, streaming, data handling) differs by provider and should be verified per engine.
Listed under
Get started
Create an account, generate an API key, and make a first request using the developer docs.
- Create a Telnyx account at the sign-up page.
- Generate an API key in the Telnyx portal.
- Make a first authenticated request using the Developer Docs, then configure the STT engine for your audio stream.
Plans and prices
Prices in USDUsage-based per-minute pricing for STT; the page states rates starting at $0.015/minute and volume contracts, without a full rate table. Confirm engine-specific rates and any minimums on the Telnyx pricing page.
- Usage-based billing
- Engine-dependent rates
Source: telnyx.com/products/speech-to-text-api, checked 29 Oct 2026. Prices can change; check before you buy.
Sources for this overview
Product pages, documentation, and pricing checked 29 Oct 2026. Each source supports part of the overview; availability and prices can change.
- Speech-to-Text API ↗telnyx.com
- Telnyx Developer Docs - Telnyx ↗developers.telnyx.com
- Infrastructure for realtime agents | Telnyx ↗telnyx.com
Ratings and reviews
No ratings for Telnyx Speech-to-Text yet.
What’s changed
Free accountSignals
Free accountData and security
Free accountCompare with similar tools
Free accountWhere this comes from
How we research- Company website
- telnyx.com: product, pricing and policy pages
- Social accounts
- Accounts the company links, and its posts on X
- Human review
- Checked by a person
- knowledge_base
- manual_review
Last checked 29 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.