Speech to text
Chinese (Mandarin) speech to text
Mandarin Chinese transcripts in simplified characters. Giggy transcribes Chinese (Mandarin) recordings for $0.04 an hour on Fast and live Chinese (Mandarin) audio for $0.08 an hour on Streaming.
Speech to text: what you pay
| Provider | Mode or model | USD per audio hour |
|---|---|---|
| Giggy | Fast | $0.040 |
| AssemblyAI | Universal-2 | $0.150 |
| OpenAI | gpt-4o-mini-transcribe | $0.180 |
| Google Cloud | Speech-to-Text V2 · Dynamic batch | $0.180 |
| Azure | Speech · Batch transcription | $0.180 |
| ElevenLabs | Scribe v3 | $0.200 |
| AssemblyAI | Universal-3.5 Pro | $0.210 |
| Deepgram | Nova-3 · Pre-recorded | $0.258 |
| Deepgram | Nova-3 Multilingual · Pre-recorded | $0.312 |
| OpenAI | Whisper / gpt-4o-transcribe | $0.360 |
| Amazon | Transcribe · Standard batch | $0.360 |
| Provider | Mode or model | USD per audio hour |
|---|---|---|
| Giggy | Streaming | $0.080 |
| Soniox | stt-rt-v5 · Streaming (est.) | $0.120 |
| ElevenLabs | Scribe v2 Realtime | $0.220 |
| Speechmatics | Linden-1 · Agent STT | $0.300 |
| OpenAI | GPT-4o Transcribe (est.) | $0.360 |
| Speechmatics | Real-time Enhanced | $0.430 |
| AssemblyAI | Universal-3.6 Pro Realtime | $0.450 |
| Deepgram | Nova-3 · English streaming | $0.462 |
| Deepgram | Flux Multilingual · Streaming | $0.468 |
| Google Cloud | Gemini 3.5 Transcribe Live (est.) | $0.536 |
| Amazon | Transcribe · Standard Streaming | $0.600 |
| Google Cloud | Chirp 3 · Streaming | $0.960 |
| Azure | Speech · Standard realtime | $1.00 |
| OpenAI | GPT-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.
Chinese (Mandarin) accuracy, published
Error rate on the FLEURS Chinese (Mandarin) test set (945 recordings). Lower is better.
| Model | Error rate |
|---|---|
| Giggy Streaming | 8.5% |
| Gemini 3.5 Transcribe Live (est.) | 9.4% |
| Scribe v2 Realtime | 10.1% |
| Speech · Standard realtime | 11.5% |
| Transcribe · Standard Streaming | 12.3% |
| Universal-3.6 Pro Realtime | 14.0% |
| GPT-4o Transcribe (est.) | 17.4% |
| Real-time Enhanced | 33.8% |
Transcribe Chinese (Mandarin) in three steps
Upload or stream Chinese (Mandarin) audio
Upload a recording, or open a WebSocket for live Chinese (Mandarin) 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 Chinese (Mandarin) 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 Chinese (Mandarin) customer calls for quality review, search and summaries.
Meetings and interviews
Turn Chinese (Mandarin) meetings and interviews into text you can quote, search and share.
Podcasts and video
Create Chinese (Mandarin) transcripts for podcasts and videos to edit, publish and caption.
Voice agents
Give Chinese (Mandarin) voice agents live speech recognition over a WebSocket.
Lectures and courses
Turn recorded Chinese (Mandarin) lessons into scripts and study notes.
Voice notes
Convert Chinese (Mandarin) 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 Chinese (Mandarin) transcription into your product
Send Chinese (Mandarin) audio to /v1/audio/transcriptions with your API key, or use the Python and JavaScript SDKs or the Giggy MCP server. Giggy detects Chinese (Mandarin) automatically, or you can set the language explicitly for the most consistent results.
Frequently asked questions
What is Chinese (Mandarin) speech to text?
Speech to text turns spoken Chinese (Mandarin) audio into written text. Giggy transcribes Chinese (Mandarin) recordings and live audio in the app or through the API.
How much does Chinese (Mandarin) 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 Chinese (Mandarin) 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 Chinese (Mandarin) audio?
Yes. Live Chinese (Mandarin) 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 Chinese (Mandarin) recording be?
Batch accepts recordings up to 25 minutes. Fast and uploaded-recording Streaming accept up to 12 hours.