Baidu ERNIE Speech
Baidu's ERNIE-aligned speech models inside ERNIE Bot Cloud.
Baidu's ERNIE-aligned speech models inside ERNIE Bot Cloud.
Best for mandarin-first workflows wanting Baidu's ERNIE-aligned speech features. Pricing: tiered RMB-per-call.
What it is
Baidu ERNIE Speech ties Baidu's ERNIE foundation models to its speech recognition stack, exposing speech-to-text plus higher-level analysis (intent, semantics) tuned for Mandarin. Sold inside ERNIE Bot Cloud (Wenxin Qianfan). China-first; international customers should verify access. Best fit: mandarin-first workflows wanting baidu's ernie-aligned speech features. Caveats: china-first; international docs limited. Pricing as listed: tiered RMB-per-call. Feature flags from vendor docs: streaming. Directory tags: commercial-api, regional-asia, foundation-model. Last vendor-page check: 2026-05-12. The product slots into the broader voice-AI tooling landscape and is best evaluated head-to-head with adjacent vendors in its subcategory; verify current language coverage, region availability, and compliance terms on the vendor's public docs at time of build.
Watch out for: China-first; international docs limited.
Install / use
Baidu ERNIE Bot Cloud speech endpointsFeatures
| Speaker diarization | No |
| Word-level timestamps | No |
| Streaming / real-time | Yes |
| Languages supported | None |
| HIPAA eligible | No |
Baidu ERNIE Speech vs Whipscribe
| Feature | Baidu ERNIE Speech | Whipscribe |
|---|---|---|
| Category | Transcription APIs | Transcription APIs |
| Pricing | tiered RMB-per-call | free beta |
| Speaker diarization | — | Yes |
| Word timestamps | — | Yes |
| Streaming | Yes | No |
| Languages | — | 99 |
| Platforms | API | Web, API, MCP |
Alternatives to Baidu ERNIE Speech
Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.