Skip to content

Run Together AI transcription with Sapat in Daytona#225

Open
katlark wants to merge 1 commit into
daytonaio:mainfrom
katlark:together-ai-sapat-guide
Open

Run Together AI transcription with Sapat in Daytona#225
katlark wants to merge 1 commit into
daytonaio:mainfrom
katlark:together-ai-sapat-guide

Conversation

@katlark
Copy link
Copy Markdown

@katlark katlark commented May 20, 2026

/claim #13

Summary

  • add a long-form Daytona guide for running Sapat with a new Together AI speech-to-text provider
  • add a companion definition for speech-to-text provider routing
  • add a first-time author profile and original SVG workflow diagram
  • link the companion Sapat provider implementation: Add Together AI transcription provider nibzard/sapat#29

Companion implementation

  • nibzard/sapat#29 adds --api together, uploads converted audio to Together AI audio transcriptions, reads credentials from TOGETHER_API_KEY, supports optional TOGETHER_MODEL and TOGETHER_API_ENDPOINT, and includes mocked coverage for request construction, transcript extraction, missing config, and CLI routing.

Validation

Daytona content PR:

  • ./node_modules/.bin/markdownlint guides/20260520_together_ai_sapat_transcription_daytona.md definitions/20260520_definition_speech_to_text_provider_routing.md authors/kat_lark.md
  • python3 -c "import xml.etree.ElementTree as ET; ET.parse(\"guides/assets/20260520_together_ai_sapat_transcription_daytona_img1.svg\"); print(\"svg ok\")"
  • git diff --check
  • wc -w guides/20260520_together_ai_sapat_transcription_daytona.md definitions/20260520_definition_speech_to_text_provider_routing.md authors/kat_lark.md (1,722 words total; guide is 1,515 words)

Companion Sapat PR:

  • PYTHONPATH=src .venv/bin/python -m unittest discover -s tests -v
  • PYTHONPATH=src .venv/bin/python -m py_compile src/sapat/script.py src/sapat/transcription/together.py tests/test_together_transcription.py tests/test_script.py
  • PYTHONPATH=src .venv/bin/python -m sapat.script --help
  • git diff --check

Notes

  • I closed my earlier IBM Watson duplicate (Run IBM Watson transcription with Sapat in Daytona #224 / Add IBM Watson Speech to Text provider nibzard/sapat#28) after seeing another contributor had registered and submitted that slice first.
  • npm run lint:md still fails on pre-existing markdownlint issues in older repository files outside this PR, including articles/20241212_Prebuilds_in_Daytona.md, definitions/20240819_definition_embedding.md, and guides/20240819_history_embedding.md.
  • Sources checked: Sapat README/source, Together AI speech-to-text docs, and Together AI audio transcription API reference.
  • No API keys, recordings, payment details, private account data, or local sensitive paths are included.

Signed-off-by: katlark <pumped_debuts_9o@icloud.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant