Mandarin Speech-to-Text

Get started Learn more

Convert Mandarin speech to text with industry-leading accuracy. Real-time voice agents and batch transcription through a single API.

Universal-3 Pro

Try uploading a file containing Mandarin speaking audio.

import assemblyai as aai

aai.settings.api_key = "YOUR_API_KEY"

audio_file = "https://assembly.ai/wildfires.mp3"

config = aai.TranscriptionConfig(
    speech_models=["universal-3-pro", "universal-2"],
    language_detection=True,
    speaker_labels=True,
)

transcript = aai.Transcriber().transcribe(audio_file, config=config)

if transcript.status == aai.TranscriptStatus.error:
    raise RuntimeError(f"Transcription failed: {transcript.error}")

print(transcript.text)

for utterance in transcript.utterances:
    print(f"Speaker {utterance.speaker}: {utterance.text}")

Mandarin Speech-to-Text

Built for every Mandarin workflow

From call centers in Beijing to media companies in Shanghai — one API for transcription, understanding, and scale.

One API, no language-specific infrastructure

One integration for Mandarin transcription, Audio Intelligence, and Voice Agents — cloud or self-hosted, fully compliant.

Accurate Mandarin transcription across every dialect

Skip the translation layer and transcribe Mandarin audio accurately, even with cross-talk and background noise.

One price, every Mandarin dialect

Flat pricing across all Mandarin dialects with transcription, summaries, sentiment, and streaming in one integration.

Mandarin Speech-to-Text

Speech-to-Text Capabilities

Enable any combination of features with a single request. Mix, match, and scale as your application grows.

Speaker identification

Label speakers by name using audio context. Supports custom profiles and multi-speaker conversations.

Entity detection

Identify names, organizations, locations, dates, and other entities across every Mandarin transcript.

Automatic Language Detection

Identify when audio is spoken in Mandarin and transcribe without pre-selecting a language.

Custom formatting

Normalize dates, phone numbers, and email addresses to machine-readable formats automatically.

PII redaction

Automatically remove sensitive data like credit cards, phone numbers, and personal information from Mandarin transcripts and audio.

Translation

Transcribe in any of 99+ languages in the same API request.

Custom spelling

Boost recognition of Mandarin brand names, product terms, and domain-specific vocabulary.

Multi-channel transcription

Transcribe separate audio channels independently — ideal for Mandarin call center recordings.

Subtitle export (SRT/VTT)

Export ready-to-use SRT and VTT caption files for Mandarin video and audio.

Language Overview

Mandarin Language Information

Dialects: Standard Mandarin (Putonghua), Taiwanese Mandarin.

Official language in: China, Taiwan, and Singapore.

Spoken in: mainland China, Taiwan, Singapore, and Chinese communities worldwide.

Compare our models

Model

Universal-3 Pro Domain-specific async audio

Universal-2 High-volume async audio

U-3 Pro Streaming Real-time voice agents, AI scribes

Universal-Streaming Multilingual Global contact centers

Mandarin Language Support

Coming soon

—

Price

$0.21 /hr

$0.15 /hr

Natural language prompting

Up to ~1,500 words

—

Up to ~1,500 words

—

Keyterm prompting

Code-switching

—

Medical Mode

—

Speaker diarization

10+ speakers

HIPAA BAA

On request

Unlimited concurrency

AI Speech-to-Text transcription in 98 languages

Our AI Speech-to-Text transcription supports every language below—just select a language and upload your audio file.

🇿🇦 Afrikaans 🇦🇱 Albanian 🇪🇹 Amharic 🇸🇦 Arabic 🇦🇲 Armenian 🇮🇳 Assamese 🇦🇿 Azerbaijani 🇷🇺 Bashkir 🇪🇸 Basque 🇧🇾 Belarusian 🇧🇩 Bengali 🇧🇦 Bosnian 🇫🇷 Breton 🇧🇬 Bulgarian 🇲🇲 Burmese 🇪🇸 Catalan 🇭🇷 Croatian 🇨🇿 Czech 🇩🇰 Danish 🇳🇱 Dutch 🇬🇧 English 🇪🇪 Estonian 🇫🇴 Faroese 🇫🇮 Finnish 🇫🇷 French 🇪🇸 Galician 🇬🇪 Georgian 🇩🇪 German 🇬🇷 Greek 🇮🇳 Gujarati 🇭🇹 Haitian Creole 🇳🇬 Hausa 🇺🇸 Hawaiian 🇮🇱 Hebrew 🇮🇳 Hindi 🇭🇺 Hungarian 🇮🇸 Icelandic 🇮🇩 Indonesian 🇮🇹 Italian 🇯🇵 Japanese 🇮🇩 Javanese 🇮🇳 Kannada 🇰🇿 Kazakh 🇰🇭 Khmer 🇰🇷 Korean 🇱🇦 Lao 🇻🇦 Latin 🇱🇻 Latvian 🇨🇩 Lingala 🇱🇹 Lithuanian 🇱🇺 Luxembourgish 🇲🇰 Macedonian 🇲🇬 Malagasy 🇲🇾 Malay 🇮🇳 Malayalam 🇲🇹 Maltese 🇨🇳 Mandarin 🇳🇿 Maori 🇮🇳 Marathi 🇲🇳 Mongolian 🇳🇵 Nepali 🇳🇴 Norwegian 🇫🇷 Occitan 🇦🇫 Pashto 🇮🇷 Persian 🇵🇱 Polish 🇵🇹 Portuguese 🇮🇳 Punjabi 🇷🇴 Romanian 🇷🇺 Russian 🇮🇳 Sanskrit 🇷🇸 Serbian 🇿🇼 Shona 🇵🇰 Sindhi 🇱🇰 Sinhala 🇸🇰 Slovak 🇸🇮 Slovenian 🇸🇴 Somali 🇪🇸 Spanish 🇮🇩 Sundanese 🇹🇿 Swahili 🇸🇪 Swedish 🇵🇭 Tagalog 🇹🇯 Tajik 🇮🇳 Tamil 🇷🇺 Tatar 🇮🇳 Telugu 🇹🇭 Thai 🇨🇳 Tibetan 🇹🇷 Turkish 🇹🇲 Turkmen 🇺🇦 Ukrainian 🇵🇰 Urdu 🇺🇿 Uzbek 🇻🇳 Vietnamese 🏴󠁧󠁢󠁷󠁬󠁳󠁿 Welsh 🇮🇱 Yiddish 🇳🇬 Yoruba