Skip to main content

Speech-to-text overview

Choose the right model for real-time or file-based speech recognition.

Migrate from closed-source models

Map your current Whisper, Deepgram, or Google ASR service to a Bailian equivalent.

Use case

Closed-source examples

Bailian recommendation

Real-time recognitionDeepgram Nova-3, Google Chirp 3Input methods and voice messages：qwen-audio-3.1-asr-flash-message
Continuous transcription：qwen-audio-3.1-asr-flash-streaming
Offline / file transcriptionOpenAI gpt-4o-transcribe, Whisperqwen-audio-3.1-asr-flash-filetrans, qwen-audio-3.1-asr-flash
Use the four "Selection criteria"—real-time vs. offline, domain terminology, speaker diarization, and emotion recognition—to identify the right model. Then check "Recommended models" for top picks per scenario, "All models" for the full version list by model family, and "Audio specifications" for input constraints. Supported languages (including dialects) are listed under each model family in "All models".

Selection criteria

Evaluate four dimensions to find the right model.

Real-time or offline?

Real-time recognition returns results as the user speaks. Offline recognition transcribes a pre-recorded file after recording ends.
  • Real-time recognition streams audio over WebSocket. Choose by use case:
    • Short voice input, such as input methods and voice messages: use qwen-audio-3.1-asr-flash-message for low first-text and overall latency, optional text polishing, and a revised final result when a speech segment ends.
    • Continuous transcription, such as meetings and classroom notes: use qwen-audio-3.1-asr-flash-streaming when users read results as they arrive and intermediate-result accuracy is a priority.
  • Offline (file transcription): Uses an HTTP API to submit audio files and retrieve transcription results. Suited for call center recordings, podcasts, and interviews. Recommended model: qwen-audio-3.1-asr-flash-filetrans (hot words, prompt context, speaker diarization).
For client integrations that require stable latency, resilience on weak networks, and full-duplex noise suppression and echo cancellation, see the AOQ protocol comparison and supported models in Realtime API overview. For HTTP, WebSocket, and SDK integration options, see Speech recognition API reference. Refer to the corresponding SDK documentation for supported models and parameters. For real-time integration, see Real-time speech recognition. For offline integration, see Non-real-time speech recognition.

Domain terminology

Two approaches, ranked by flexibility:
  1. Prompt context injection: Describe your domain in the system prompt. No setup required—the model adapts per request. Recommended models: qwen-audio-3.1-asr-flash-streaming, qwen-audio-3.1-asr-flash-filetrans, and qwen-audio-3.1-asr-flash.
  2. Hot words: Supply a weighted vocabulary list. Recommended models: qwen-audio-3.1-asr-flash-streaming, qwen-audio-3.1-asr-flash-filetrans, and qwen-audio-3.1-asr-flash.
qwen-audio-3.1-asr-flash-message supports instant hot words, precompiled hot words, and conversation context. Set vocabulary or vocabulary_id for hot words, and pass previous user transcriptions and assistant replies through input.context. For parameter definitions, see Client events.

Speaker diarization

qwen-audio-3.1-asr-flash, qwen-audio-3.1-asr-flash-filetrans, qwen-audio-3.0-asr-flash-filetrans, and Fun-ASR offline models (fun-asr) support speaker diarization. To identify who said what, use qwen-audio-3.1-asr-flash-filetrans.

Emotion recognition

Qwen-ASR models detect emotions alongside transcription. Recommended models: qwen3-asr-flash-realtime (real-time) or qwen3-asr-flash-filetrans (offline). Top picks for common scenarios.

Model ID

Mode

API

Accuracy boost

Emotion recognition

Speaker diarization

Languages

Max audio duration/size

qwen-audio-3.1-asr-flash-messageReal-timeWebSocketHot words, ContextUnsupportedUnsupportedMultilingual with dialects—
qwen-audio-3.1-asr-flash-streamingReal-timeWebSocketHot words, prompt contextUnsupportedUnsupportedMultilingual with dialectsUnlimited
qwen-audio-3.1-asr-flash-filetransOfflineHTTPHot words, prompt contextUnsupportedSupportedMultilingual with dialects12 hours / 2 GB

All models

Qwen-Audio-ASR-Message

Model IDModeAPIAccuracy boostEmotion recognitionSpeaker diarizationLanguagesMax audio duration/size
qwen-audio-3.1-asr-flash-messageReal-timeWebSocketHot words, ContextUnsupportedUnsupportedMultilingual with dialects—
Supported languages:
  • qwen-audio-3.1-asr-flash-message: Chinese (Mandarin, Cantonese, Wu, Hokkien, Hakka, Gan, Xiang, Jin; plus regional accents including Central Plains, Southwestern, Ji-Lu, Jianghuai, Lan-Yin, Jiao-Liao, Northeastern, Beijing, and Hong Kong/Taiwan—covering Henan, Shaanxi, Hubei, Sichuan, Chongqing, Yunnan, Guizhou, Guangdong, Guangxi, Hebei, Tianjin, Shandong, Anhui, Nanjing, Jiangsu, Hangzhou, Gansu, and Ningxia accents), English, Japanese, Korean, Vietnamese, Thai, Indonesian, Malay, Filipino, Hindi, Arabic, French, German, Spanish, Portuguese, Russian, Italian, Dutch, Swedish, Danish, Finnish, Norwegian, Greek, Polish, Czech, Hungarian, Romanian, Bulgarian, Croatian, Slovak

Qwen-Audio-ASR-Streaming

Model ID

Mode

API

Accuracy boost

Emotion recognition

Speaker diarization

Languages

Max audio duration/size

qwen-audio-3.1-asr-flash-streamingReal-timeWebSocketHot words, prompt contextUnsupportedUnsupportedMultilingual with dialectsUnlimited
qwen-audio-3.0-asr-flash-streamingReal-timeWebSocketHot words, prompt contextUnsupportedUnsupportedMultilingual with dialectsUnlimited
Supported languages (by version):
  • qwen-audio-3.1-asr-flash-streaming, qwen-audio-3.0-asr-flash-streaming: Chinese (Mandarin, Cantonese, Wu, Hokkien, Hakka, Gan, Xiang, Jin; plus regional accents including Central Plains, Southwestern, Ji-Lu, Jianghuai, Lan-Yin, Jiao-Liao, Northeastern, Beijing, and Hong Kong/Taiwan—covering Henan, Shaanxi, Hubei, Sichuan, Chongqing, Yunnan, Guizhou, Guangdong, Guangxi, Hebei, Tianjin, Shandong, Anhui, Nanjing, Jiangsu, Hangzhou, Gansu, and Ningxia accents), English, Japanese, Korean, Vietnamese, Thai, Indonesian, Malay, Filipino, Hindi, Arabic, French, German, Spanish, Portuguese, Russian, Italian, Dutch, Swedish, Danish, Finnish, Norwegian, Greek, Polish, Czech, Hungarian, Romanian, Bulgarian, Croatian, Slovak

Qwen-Audio-ASR-Filetrans

Model ID

Mode

API

Accuracy boost

Emotion recognition

Speaker diarization

Languages

Max audio duration/size

qwen-audio-3.1-asr-flash-filetransOfflineHTTPHot words, prompt contextUnsupportedSupportedMultilingual with dialects12 hours / 2 GB
qwen-audio-3.0-asr-flash-filetransOfflineHTTPHot words, prompt contextUnsupportedSupportedMultilingual with dialects12 hours / 2 GB
Supported languages (by version):
  • qwen-audio-3.1-asr-flash-filetrans, qwen-audio-3.0-asr-flash-filetrans: Chinese (Mandarin, Cantonese, Wu, Hokkien, Hakka, Gan, Xiang, Jin; plus regional accents including Central Plains, Southwestern, Ji-Lu, Jianghuai, Lan-Yin, Jiao-Liao, Northeastern, Beijing, and Hong Kong/Taiwan—covering Henan, Shaanxi, Hubei, Sichuan, Chongqing, Yunnan, Guizhou, Guangdong, Guangxi, Hebei, Tianjin, Shandong, Anhui, Nanjing, Jiangsu, Hangzhou, Gansu, and Ningxia accents), English, Japanese, Korean, Vietnamese, Thai, Indonesian, Malay, Filipino, Hindi, Arabic, French, German, Spanish, Portuguese, Russian, Italian, Dutch, Swedish, Danish, Finnish, Norwegian, Greek, Polish, Czech, Hungarian, Romanian, Bulgarian, Croatian, Slovak

Qwen-Audio-ASR

Model ID

Mode

API

Accuracy boost

Emotion recognition

Speaker diarization

Languages

Max audio duration/size

qwen-audio-3.1-asr-flashOfflineHTTPHot words, prompt contextUnsupportedSupportedMultilingual with dialects5 minutes / 2 GB
qwen-audio-3.0-asr-flashOfflineHTTPHot words, prompt contextUnsupportedUnsupportedMultilingual with dialects5 minutes / 2 GB
Supported languages (by version):
  • qwen-audio-3.1-asr-flash, qwen-audio-3.0-asr-flash: Chinese (Mandarin, Cantonese, Wu, Hokkien, Hakka, Gan, Xiang, Jin; plus regional accents including Central Plains, Southwestern, Ji-Lu, Jianghuai, Lan-Yin, Jiao-Liao, Northeastern, Beijing, and Hong Kong/Taiwan—covering Henan, Shaanxi, Hubei, Sichuan, Chongqing, Yunnan, Guizhou, Guangdong, Guangxi, Hebei, Tianjin, Shandong, Anhui, Nanjing, Jiangsu, Hangzhou, Gansu, and Ningxia accents), English, Japanese, Korean, Vietnamese, Thai, Indonesian, Malay, Filipino, Hindi, Arabic, French, German, Spanish, Portuguese, Russian, Italian, Dutch, Swedish, Danish, Finnish, Norwegian, Greek, Polish, Czech, Hungarian, Romanian, Bulgarian, Croatian, Slovak

Fun-ASR

Model ID

Mode

API

Accuracy boost

Emotion recognition

Speaker diarization

Languages

Max audio duration/size

fun-asr-realtimeReal-timeWebSocketHot wordsUnsupportedUnsupportedMultilingual with dialectsUnlimited
fun-asr-realtime-2026-02-28Real-timeWebSocketHot wordsUnsupportedUnsupportedChinese, English, Japanese, and dialectsUnlimited
fun-asr-flash-8k-realtimeReal-timeWebSocketHot wordsUnsupportedUnsupportedChineseUnlimited
fun-asr-flash-8k-realtime-2026-01-28Real-timeWebSocketHot wordsUnsupportedUnsupportedChineseUnlimited
fun-asrOfflineHTTPHot wordsUnsupportedSupportedMultilingual with dialects12 hours / 2 GB
fun-asr-flash-2026-06-15OfflineHTTPPrompt contextUnsupportedUnsupportedMultilingual with dialects5 minutes / 2 GB
Supported languages (by version):
  • Fun-ASR-Realtime main version (fun-asr-realtime): Chinese (Mandarin, Cantonese, Wu, Hokkien, Hakka, Gan, Xiang, Jin; plus regional accents including Central Plains, Southwestern, Ji-Lu, Jianghuai, Lan-Yin, Jiao-Liao, Northeastern, Beijing, and Hong Kong/Taiwan—covering Henan, Shaanxi, Hubei, Sichuan, Chongqing, Yunnan, Guizhou, Guangdong, Guangxi, Hebei, Tianjin, Shandong, Anhui, Nanjing, Jiangsu, Hangzhou, Gansu, and Ningxia accents), English, Japanese, Korean, Vietnamese, Thai, Indonesian, Malay, Filipino, Hindi, Arabic, French, German, Spanish, Portuguese, Russian, Italian, Dutch, Swedish, Danish, Finnish, Norwegian, Greek, Polish, Czech, Hungarian, Romanian, Bulgarian, Croatian, Slovak
  • fun-asr-realtime-2026-02-28: Chinese (Mandarin, Cantonese, Wu, Hokkien, Hakka, Gan, Xiang, Jin; plus regional accents including Central Plains, Southwestern, Ji-Lu, Jianghuai, Lan-Yin, Jiao-Liao, Northeastern, Beijing, and Hong Kong/Taiwan—covering Henan, Shaanxi, Hubei, Sichuan, Chongqing, Yunnan, Guizhou, Guangdong, Guangxi, Hebei, Tianjin, Shandong, Anhui, Nanjing, Jiangsu, Hangzhou, Gansu, and Ningxia accents), English, Japanese
  • Fun-ASR-Flash-Realtime(8K) (fun-asr-flash-8k-realtime, fun-asr-flash-8k-realtime-2026-01-28): Chinese
  • Fun-ASR main versions (fun-asr): Chinese (Mandarin, Cantonese, Wu, Hokkien, Hakka, Gan, Xiang, Jin; plus regional accents including Central Plains, Southwestern, Ji-Lu, Jianghuai, Lan-Yin, Jiao-Liao, Northeastern, Beijing, and Hong Kong/Taiwan—covering Henan, Shaanxi, Hubei, Sichuan, Chongqing, Yunnan, Guizhou, Guangdong, Guangxi, Hebei, Tianjin, Shandong, Anhui, Nanjing, Jiangsu, Hangzhou, Gansu, and Ningxia accents), English, Japanese, Korean, Vietnamese, Thai, Indonesian, Malay, Filipino, Hindi, Arabic, French, German, Spanish, Portuguese, Russian, Italian, Dutch, Swedish, Danish, Finnish, Norwegian, Greek, Polish, Czech, Hungarian, Romanian, Bulgarian, Croatian, Slovak
  • Fun-ASR-Flash (fun-asr-flash-2026-06-15): Chinese (Mandarin, Cantonese, Wu, Hokkien, Hakka, Gan, Xiang, Jin; plus regional accents including Central Plains, Southwestern, Ji-Lu, Jianghuai, Lan-Yin, Jiao-Liao, Northeastern, Beijing, and Hong Kong/Taiwan—covering Henan, Shaanxi, Hubei, Sichuan, Chongqing, Yunnan, Guizhou, Guangdong, Guangxi, Hebei, Tianjin, Shandong, Anhui, Nanjing, Jiangsu, Hangzhou, Gansu, and Ningxia accents), English, Japanese, Korean, Vietnamese, Thai, Indonesian, Malay, Filipino, Hindi, Arabic, French, German, Spanish, Portuguese, Russian, Italian, Dutch, Swedish, Danish, Finnish, Norwegian, Greek, Polish, Czech, Hungarian, Romanian, Bulgarian, Croatian, Slovak

Qwen-ASR

Model ID

Mode

API

Accuracy boost

Emotion recognition

Speaker diarization

Languages

Max audio duration/size

qwen3-asr-flash-realtimeReal-timeWebSocketUnsupportedSupportedUnsupportedMultilingual with dialectsUnlimited
qwen3-asr-flash-filetransOfflineHTTPUnsupportedSupportedUnsupportedMultilingual with dialects12 hours / 2 GB
qwen3-asr-flashOfflineHTTP (OpenAI-compatible)UnsupportedSupportedUnsupportedMultilingual with dialects5 minutes / 10 MB
Supported languages: All Qwen-ASR models (qwen3-asr-flash-realtime, qwen3-asr-flash-filetrans, qwen3-asr-flash) share the same language list: Chinese (Mandarin, Sichuanese, Hokkien, Wu, Cantonese), English, Japanese, German, Korean, Russian, French, Portuguese, Arabic, Italian, Spanish, Hindi, Indonesian, Thai, Turkish, Ukrainian, Vietnamese, Czech, Danish, Filipino, Finnish, Icelandic, Malay, Norwegian, Polish, Swedish.

Paraformer

Paraformer is an older-generation ASR model family. Migrate to Fun-ASR or Qwen-ASR when possible.

Model ID

API

Description

paraformer-realtime-v2WebSocketReal-time recognition; Chinese, English, Japanese, Korean, German, French, Russian
paraformer-realtime-8k-v2WebSocketReal-time recognition for 8 kHz telephony; Chinese
paraformer-v2HTTPFile transcription with speaker diarization; Chinese, English, Japanese, Korean, German, French, Russian
paraformer-8k-v2HTTPFile transcription for 8 kHz telephony; Chinese
Supported languages (by version):
  • paraformer-realtime-v2, paraformer-v2: Chinese (Mandarin, Cantonese, Wu, Hokkien, Northeastern, Gansu, Guizhou, Henan, Hubei, Hunan, Ningxia, Shanxi, Shaanxi, Shandong, Sichuan, Tianjin, Jiangxi, Yunnan, Shanghai), English, Japanese, Korean, German, French, Russian
  • paraformer-realtime-8k-v2, paraformer-8k-v2: Chinese (Mandarin)

Audio specifications

Audio specifications for real-time and offline modes. For supported languages, see the model family subsection under "All models".

Real-time

Model ID

Input method

Audio format

Sample rate

Size/duration

qwen-audio-3.1-asr-flash-messageBinary streampcm, wav, mp3, opus, speex, aac, amr16 kHz—
qwen-audio-3.1-asr-flash-streaming, qwen-audio-3.0-asr-flash-streamingBinary streampcm, wav, mp3, opus, speex, aac, amrAnyUnlimited
Fun-ASR-Realtime series (fun-asr-realtime, etc.)Binary streampcm, wav, mp3, opus, speex, aac, amrAnyUnlimited
Fun-ASR-Flash-8K-Realtime series (fun-asr-flash-8k-realtime, etc.)Binary streamSame as Fun-ASR-Realtime8 kHzUnlimited
qwen3-asr-flash-realtimeBinary streampcm, opus8 kHz, 16 kHzUnlimited
paraformer-realtime-v2, paraformer-realtime-8k-v2Binary streamSame as Fun-ASR-Realtimeparaformer-realtime-v2 any rate; paraformer-realtime-8k-v2 8 kHzUnlimited
All real-time models accept mono (single-channel) input only.

Offline

Model ID

Input method

Audio format

Sample rate

File size/duration

qwen-audio-3.1-asr-flash-filetrans, qwen-audio-3.0-asr-flash-filetransPublicly accessible file URL; 1 URL per requestaac, amr, avi, flac, flv, m4a, mkv, mov, mp3, mp4, mpeg, ogg, opus, wav, webm, wma, wmvAny≤2 GB; ≤12 hours (≤2 hours recommended when speaker diarization is enabled)
qwen-audio-3.1-asr-flashURL / Base64; 1 file per requestaac, amr, avi, flac, flv, m4a, mkv, mov, mp3, mp4, mpeg, ogg, opus, wav, webm, wma, wmvAny≤2 GB; ≤5 minutes
qwen-audio-3.0-asr-flashURL / Base64; 1 file per requestaac, amr, avi, flac, flv, m4a, mkv, mov, mp3, mp4, mpeg, ogg, opus, wav, webm, wma, wmvAny≤10 MB; ≤5 minutes
fun-asrPublicly accessible file URL; 1 URL per requestaac, amr, avi, flac, flv, m4a, mkv, mov, mp3, mp4, mpeg, ogg, opus, wav, webm, wma, wmvAny≤2 GB; ≤12 hours (≤2 hours recommended when speaker diarization is enabled)
fun-asr-flash-2026-06-15URL / Base64; 1 file per requestaac, amr, avi, flac, flv, m4a, mkv, mov, mp3, mp4, mpeg, ogg, opus, wav, webm, wma, wmvAny≤2 GB; ≤5 minutes
fun-asr-realtime, fun-asr-realtime-2026-02-28URL / Base64; 1 file per requestaac, amr, avi, flac, flv, m4a, mkv, mov, mp3, mp4, mpeg, ogg, opus, wav, webm, wma, wmvAny≤2 GB; ≤5 minutes
paraformer-v2, paraformer-8k-v2Same as Fun-ASRSame as Fun-ASRparaformer-v2 /v1 any rate; paraformer-8k-v2 8 kHz onlySame as Fun-ASR
qwen3-asr-flash-filetransPublicly accessible file URL; 1 URL per requestaac, amr, avi, flac, flv, m4a, mkv, mov, mp3, mp4, mpeg, ogg, opus, wav, webm, wma, wmvpcm requires 16 kHz; other formats accept any rate (the server resamples to 16 kHz before recognition)≤2 GB; ≤12 hours
qwen3-asr-flashURL / Base64 / local file absolute path; 1 file per requestaac, amr, avi, aiff, flac, flv, mkv, mp3, mpeg, ogg, opus, wav, webm, wma, wmvpcm requires 16 kHz; other formats accept any rate (the server resamples to 16 kHz before recognition)≤10 MB; ≤5 minutes
Get Started
Billing
Token Plan
Model Playground
Clients and Developer Tools
Model Inference
Fine-tuning
Evaluation
Model Compression
Statistics and Monitoring
Model Data
Security and Compliance
Best Practices
Support
Changelog