Speech to text

French speech to text

French transcripts for interviews, lectures and support calls. Giggy transcribes French recordings for $0.04 an hour on Fast and live French audio for $0.08 an hour on Streaming.

Get your API key · See pricing

Speech to text: what you pay

Recorded audio, compared with Giggy Fast
ProviderMode or modelUSD per audio hour
GiggyFast$0.040
AssemblyAIUniversal-2$0.150
OpenAIgpt-4o-mini-transcribe$0.180
Google CloudSpeech-to-Text V2 · Dynamic batch$0.180
AzureSpeech · Batch transcription$0.180
ElevenLabsScribe v3$0.200
AssemblyAIUniversal-3.5 Pro$0.210
DeepgramNova-3 · Pre-recorded$0.258
DeepgramNova-3 Multilingual · Pre-recorded$0.312
OpenAIWhisper / gpt-4o-transcribe$0.360
AmazonTranscribe · Standard batch$0.360
Live audio, compared with Giggy Streaming
ProviderMode or modelUSD per audio hour
GiggyStreaming$0.080
Sonioxstt-rt-v5 · Streaming (est.)$0.120
ElevenLabsScribe v2 Realtime$0.220
SpeechmaticsLinden-1 · Agent STT$0.300
OpenAIGPT-4o Transcribe (est.)$0.360
SpeechmaticsReal-time Enhanced$0.430
AssemblyAIUniversal-3.6 Pro Realtime$0.450
DeepgramNova-3 · English streaming$0.462
DeepgramFlux Multilingual · Streaming$0.468
Google CloudGemini 3.5 Transcribe Live (est.)$0.536
AmazonTranscribe · Standard Streaming$0.600
Google CloudChirp 3 · Streaming$0.960
AzureSpeech · Standard realtime$1.00
OpenAIGPT-Live-Transcribe$1.02

All recorded-audio prices checked November 11, 2026 on each provider's pricing page or official price API. ElevenLabs, OpenAI, Deepgram, Google, Amazon, Azure and AssemblyAI checked November 11, 2026; Speechmatics October 8; Soniox token-based estimate October 20.

French accuracy, published

Error rate on the FLEURS French test set (676 recordings). Lower is better.

ModelError rate
Universal-3.6 Pro Realtime5.0%
Gemini 3.5 Transcribe Live (est.)5.4%
Giggy Streaming5.9%
Real-time Enhanced6.5%
Scribe v2 Realtime6.9%
Transcribe · Standard Streaming7.6%
GPT-4o Transcribe (est.)10.6%
Speech · Standard realtime11.4%
Flux Multilingual · Streaming13.9%

Transcribe French in three steps

  • Upload or stream French audio

    Upload a recording, or open a WebSocket for live French audio from a call, meeting or microphone.

  • Choose Batch, Fast or Streaming

    Batch transcribes recordings up to 25 minutes in a shared queue at no cost. Fast transcribes up to 12 hours with priority. Streaming returns text while people speak.

  • Get the transcript

    Batch and Fast return a transcript JSON result. Streaming sends cumulative French text as it is recognized, so the latest text always replaces the previous one.

Built for a wide range of uses

  • Calls and support

    Transcribe French customer calls for quality review, search and summaries.

  • Meetings and interviews

    Turn French meetings and interviews into text you can quote, search and share.

  • Podcasts and video

    Create French transcripts for podcasts and videos to edit, publish and caption.

  • Voice agents

    Give French voice agents live speech recognition over a WebSocket.

  • Lectures and courses

    Turn recorded French lessons into scripts and study notes.

  • Voice notes

    Convert French voice notes and dictation into text.

Priced per hour, without a subscription

Fast costs $0.04 and Streaming $0.08 per audio hour with Pro, Studio or Scale credits, billed on validated input duration. Credits are prepaid, shared across speech to text, text to speech and voice creation, and expire one calendar year after purchase.

Build French transcription into your product

Send French audio to /v1/audio/transcriptions with your API key, or use the Python and JavaScript SDKs or the Giggy MCP server. Giggy detects French automatically, or you can set the language explicitly for the most consistent results.

Read the API docs · API reference

Frequently asked questions

What is French speech to text?

Speech to text turns spoken French audio into written text. Giggy transcribes French recordings and live audio in the app or through the API.

How much does French speech to text cost?

Giggy Fast costs $0.04 per input audio hour and Streaming $0.08, with Pro, Studio or Scale credits. Batch transcription is free for recordings up to 25 minutes, subject to request and queue limits.

Does Giggy detect French automatically?

Yes. Giggy detects the spoken language automatically. You can also set the language in the API request when you already know it.

Can Giggy transcribe live French audio?

Yes. Live French speech to text runs over a WebSocket at /v1/audio/transcriptions. Paid API sessions accept up to 12 hours of live audio.

How long can a French recording be?

Batch accepts recordings up to 25 minutes. Fast and uploaded-recording Streaming accept up to 12 hours.