## Summary
Add support for Amazon Bedrock as an LLM provider using the native
**Converse API** with API Key authentication.
## Motivation
AWS Bedrock provides access to frontier models (Claude, Amazon Nova,
Llama, DeepSeek etc.) with enterprise-grade security and compliance.
Many teams running AI workloads on AWS infrastructure want to use
Bedrock directly, keeping all traffic within the AWS network.
## Implementation
- Uses Amazon Bedrock's native **Converse API**
(`bedrock-runtime.{region}.amazonaws.com/model/{modelId}/converse`)
- Authentication via **Amazon Bedrock API Key** (`Authorization: Bearer
<key>`) — no SigV4 signing, no extra dependencies
- Config: `apiKey` (Bedrock API key) + `region` (AWS region, default:
`us-east-1`)
- All Bedrock-specific config is declared via the generic
`onboardingFields` mechanism on the provider definition — no
`isAmazonBedrock` branching, no `ProviderConfigData` type changes
- Dynamic model listing via `ListFoundationModels` +
`ListInferenceProfiles` APIs, with fallback to a static list
- Streaming: calls `/converse` (standard JSON response), then re-emits
the full text as `text/event-stream` character-by-character —
bearer-token auth does not support the binary AWS Event Stream protocol
required by `/converse-stream`
## Supported Models
**Anthropic Claude (via Bedrock)**
- Claude Opus/Sonnet/Haiku 4.x
- Claude Sonnet 3.7 (hybrid reasoning)
- Claude Sonnet 3.5 v2
**Amazon Nova**
- Nova Pro (multimodal)
- Nova Lite (multimodal, low cost)
- Nova Micro (text-only, lowest cost)
**Meta / Others**
- Llama 3.3 70B Instruct
- DeepSeek, Moonshot, Minimax models available via inference profiles
## Authentication
Generate a Bedrock API key in: **AWS Console → Amazon Bedrock → API
Keys**
> Note: Long-term API keys have a 30-day expiry. AWS recommends them for
development/exploration use.
## Notes
⚠️ **CORS in browser**: Like other providers (Anthropic, etc.), direct
browser calls to Bedrock are subject to CORS restrictions. Works out of
the box in Tauri desktop app and Node.js server environments. For
browser use, a CORS proxy is needed.
## Testing
```
pnpm vitest run packages/stage-ui/src/libs/providers/providers/amazon-bedrock/index.test.ts
```
---------
Co-authored-by-agent: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
## Summary
- Add `minimax-speech` TTS provider using MiniMax's T2A v2 API
- Implement streaming SSE response with hex-encoded audio decoding (no
external dependency required)
- Include a curated static voice list (English and Mandarin voices)
- Add `speech-2.8-hd` (default) and `speech-2.8-turbo` model entries
- Support configurable base URL defaulting to `https://api.minimax.io`
- Add i18n translations for all 9 supported locales
Closes#1274
## Implementation Details
The provider uses a custom `fetch` interceptor within the
`SpeechProvider` interface to:
1. Parse the incoming OpenAI-style request (`input`, `voice`, `model`)
2. Call MiniMax's `/v1/t2a_v2` SSE streaming endpoint
3. Decode hex-encoded audio chunks from SSE events (skipping the summary
chunk with `status=2`)
4. Return a concatenated `audio/mpeg` response
## API Reference
- TTS: https://platform.minimax.io/docs/api-reference/speech-t2a-http
github-actions[bot]