Speech-to-text for French voice agents

Streaming French transcription with end-of-turn detection, so your agent replies at the right moment. Plugs into Pipecat, LiveKit, and Twilio, and follows callers who switch between French and 60+ other languages.

$0.12/hour real-time

Build with API Explore docs

Parlez à l'agent vocal Soniox en temps réel. Appuyez sur 'Start speaking'.

Need a French voice for your agent?
Try Soniox Text-to-Speech

Trusted by teams building global voice products

What a French voice agent needs from speech-to-text

To serve more than 280,000,000 French speakers across France, Democratic Republic of Congo, Canada, and beyond, a French voice agent has to handle regional accents and behave predictably in live production.

A speech-to-text system for French voice agents should:

Deliver highly accurate transcription that keeps up with live French conversations.
Run with ultra-low latency, enabling real-time LLM processing and fast responses.
Reliably detect end-of-turn speech so agents respond at the right moment.
Perform in real-world conditions with noise, accents, interruptions, and multilingual speech.
Scale economically, with pricing that works for high-volume deployments.

Soniox is built around these requirements from the ground up, delivering fast, reliable speech recognition for voice agents for French and all other 60+ supported languages. One unified model supports true multilingual and language-switching speech, without changing configurations, switching models, or restarting streams.

With real-time French language transcription starting at $0.12 per hour, Soniox makes it practical and cost-effective to deploy French voice agents at massive scale, anywhere.

“As Germany’s leading voicebot provider for automotive dealerships, Soniox has transformed our recognition of customer IDs and alphanumerics, driving much higher voicebot acceptance rates.”

Dr. Steven Zielke,
Founder & CEO of mobilApp

Low-latency French speech-to-text for voice agents

Live French transcription

Soniox is built for continuous conversational streams, returning French text as speech arrives so agents can act before the speaker is done.

Learn about French real-time transcription

Endpoint detection for French

Built-in endpoint detection gives French voice agents reliable end-of-turn signals without fragile silence timers.

Understand endpoint detection

Custom context for French

Inject brand names, jargon, and regional terms at request time to improve French accuracy without fine-tuned models.

French plus 60+ more languages

One model handles French and in-stream language switching, keeping latency stable and multilingual deployments simple.

See supported languages list

Data residency for regulated deployments

Keep French speech and transcripts in the required geography for regulated deployments.

Get more details about data residency

Why it works

Voice agents need speech recognition that is fast, predictable, multilingual, and production-ready.

Soniox combines low-latency streaming, turn detection, context control, French accuracy, and regional deployment in one real-time API.

Start building with Soniox API

Build a French voice agent

If you tried our introduction demo above, you saw the voice loop in action: streaming speech-to-text, LLM reasoning, and streaming text-to-speech working together in real time. We put the same underlying architecture into an open-source reference app you can clone, run locally, and adapt to your own use case and style.

Get your French voice agent running

The Soniox Voice Agent demo is an open-source voice-to-voice assistant you can clone, run locally, and adapt to French. The default scenario is an appointment-booking agent for a fictional car repair shop, but the same architecture works for any voice agent (support, intake, scheduling, anything that needs to listen and speak).

How the voice loop fits together

Microphone audio runs through Silero VAD for barge-in detection, then into Soniox STT for streaming transcription with semantic endpoint detection. The transcript flows to an LLM, which streams its reply token by token straight into Soniox TTS. Soniox TTS is itself a real-time full-duplex streaming model: text flows in on the WebSocket while audio flows out on the same connection at the same time. It starts streaming back audio from the first few words, and as the LLM keeps producing tokens, Soniox keeps turning them into audio as they arrive. The user hears the reply as it forms, with no wait for the LLM to finish before the voice starts.

What's in the repo

Python server: orchestrates VAD, STT, LLM, and TTS, and holds the conversation state.
React frontend: captures mic audio in the browser and plays the agent's reply.
Twilio proxy (optional): connect the same agent to a phone number.

Get it running

Create an account on Soniox Console and generate your Soniox API key.
Clone Soniox Examples repo that contains apps/soniox-voice-bot-demo code and follow the READMEs in the /server and /frontend folders to install dependencies and set your API key.
Adapt the system prompt, STT language hints and TTS language to French. See STT language hints and TTS supported languages.
Start the server and the frontend, open it in your browser, and have a French conversation.

Learn more about the demo and all possible STT and TTS API configurations and concepts from our comprehensive docs page.

Plug Soniox into your framework of choice

If you don't want to wire up the voice loop yourself, and you're already using a popular voice-agent framework, Soniox plugs in as the STT and TTS through ready-made integrations.

Pipecat (voice-agent framework): drop in Soniox STT and TTS through the official STT and TTS packages.
LiveKit (real-time audio platform): use Soniox as the speech layer for LiveKit voice agents in the browser, on mobile, or over telephony.

Soniox also provides official integrations with LangChain, Twilio, n8n and other integrations.

Use Soniox in popular frameworks

Soniox integrates seamlessly with leading real-time communication platforms, AI frameworks, automation tools, and developer SDKs.

An open source framework and developer platform for building, testing, deploying, scaling, and observing agents in production.

View docs

Open source framework for voice and multimodal conversational AI.

View docs

Twilio is a cloud-based customer engagement platform (CPaaS) that provides APIs, allowing developers to integrate voice, messaging (SMS, WhatsApp), email, and authentication capabilities into applications.

View docs

Open-source development framework designed to build applications powered by large language models (LLMs).

View docs

The open-source AI toolkit designed to help developers build AI-powered applications and agents with React, Next.js, Vue, Svelte, Node.js, and more.

View docs

Open-source AI SDK with a unified interface across multiple providers. No vendor lock-in, no proprietary formats.

View docs

n8n is a powerful, low-code/pro-code workflow automation tool that connects various applications, APIs, and databases to automate tasks.

View docs

Build the next generation of voice products, from agents and wearables to dictation, translation, and real-time multilingual experiences.

Build with API

French voice agents for every use case

Smart assistants in French

Deliver fast, natural voice interactions in French to help answer questions or complete tasks in speaker's native language.

Customer support

Support agents can instantly handle French -speaking customers without any model switching, resolving issues much faster.

In-app voice agents

Add natural French voice automation directly into your app – from onboarding to scheduling to self service – with fast, structured responses.

Call routing agents

Identify intent early and respond immediately, even before the user finishes speaking. No phone menus necessary.

Simple, usage-based pricing. Get started with real-time API for $0.12/hour.

Start building

Voice agents in 60+ languages

Also for French: the French speech-to-text API for transcription, the French text-to-speech API for your agent's voice, and the French voice AI platform for enterprise deployment.

Privacy and compliance, built right in

Never stored, never saved.

Audio stays in memory, everything is processed in real-time.

Built for privacy-critical use cases.

Adhering to leading global security, privacy, and compliance standards.

Trusted where privacy matters most.

Used in industries where speech is sensitive, from healthcare to enterprise.

SOC 2 Type 2 · ISO/IEC 27001:2022 · HIPAA · GDPR

Frequently asked questions

Which speech-to-text should I use for a French voice agent?

Use the Soniox real-time speech-to-text API, which is built for AI voice agents. It converts live French speech into text with low latency, supports streaming use cases, and works alongside more than 60 other languages without switching models or restarting the stream.

Is Soniox suitable for building French AI voice agents?

Yes. Soniox's multilingual speech model handles real-time French voice agent workflows, including streaming transcription, early token delivery, and endpoint detection for conversational turn-taking, all configurable through the API.

What makes Soniox a low-latency French speech-to-text API?

Soniox uses a real-time streaming architecture that processes French audio continuously and emits transcription results incrementally as speech arrives. This allows voice agents to begin processing French speech before an utterance is complete.

How does Soniox detect when French-speaking users finish talking?

Soniox includes built-in endpoint detection that identifies speech boundaries in French. Voice agents can use emitted end events to decide when to respond without relying on client-side silence timers.

Can I customize transcription behavior for French voice agents?

Yes. The Soniox API is configurable, allowing developers to adjust transcription behavior for French speech, including custom context for domain-specific vocabulary, eliminating the need for separate fine-tuned models.

Can Soniox handle language switching involving French within a conversation?

Yes. Soniox can recognize and transcribe speech when speakers switch between French and other supported languages mid-sentence or mid-conversation, without requiring stream restarts or language-specific routing.

Is Soniox suitable for regulated industries using French speech?

Yes. Soniox supports data residency for regulated environments such as medical and legal use cases, allowing French speech and transcript data to remain within required geographic regions while using the same real-time API.

Is French audio stored when using the Soniox API?

No. French audio is processed in real-time and kept in memory only. Soniox is designed for privacy-critical voice agent applications where speech data should not be stored by default.

How do developers get started with French speech-to-text in Soniox?

Developers can generate an API key on Soniox Console and start streaming French audio over WebSockets to Soniox immediately. The API integrates with common voice agent frameworks and real-time media pipelines.

Ready to get started?

Create an account instantly, or contact us to design a custom package for your business.

Build with API

Documentation

Get up and running in minutes and spend your time building, not wrestling with the API.

Explore docs

See what you’ll pay

Pay only for what you use with our flexible pricing. Built to scale with you.

Pricing details