Run SiliconFlow ASR with Sapat in Daytona

[shuimaoiko]

/claim #13

Summary

• Adds a long-form Daytona guide for running SiliconFlow SenseVoice transcription through Sapat in a reproducible workspace.
• Adds an OpenAI-compatible transcription endpoint definition, a first-time author profile, and an original SVG workflow diagram.
• Links the companion Sapat provider implementation: Add SiliconFlow transcription provider nibzard/sapat#68
• Keeps the guide aligned with SiliconFlow docs: the provider sends the documented file + model multipart fields and does not forward undocumented generic fields.

Validation

Content files:

• npx --yes markdownlint-cli@0.29.0 guides/20260621_run_siliconflow_asr_with_sapat_in_daytona.md definitions/20260621_definition_openai_compatible_transcription_endpoint.md authors/shuimao.md
• xmllint --noout guides/assets/20260621_run_siliconflow_asr_with_sapat_in_daytona_workflow.svg
• git diff --cached --check
• Guide word count check: 1,624 words
• Local secret-pattern scan: 0 obvious token patterns found

Companion Sapat provider PR:

• .venv/bin/python -m pytest tests/providers/test_siliconflow.py tests/test_registry.py tests/test_process.py -q
• .venv/bin/python -m pytest -q
• .venv/bin/python -m black --check sapat/providers/siliconflow.py sapat/process.py tests/providers/test_siliconflow.py tests/test_process.py
• .venv/bin/python -m compileall sapat tests/providers/test_siliconflow.py tests/test_process.py
• git diff --check

No secrets, private media, payout details, generated transcripts, or API keys are included.