Captions and transcription

Turn a recording into an SRT, review it, then decide separately whether to burn it in.

Making captions and burning them in are separate decisions, and the commands reflect that: transcribe writes a file, caption attaches one.

​

Transcribe

splice transcribe clip_1 --provider gemini --attach
splice transcribe --provider whisper --language en
splice transcribe --srt review.srt          # write somewhere else

transcribe writes captions.srt beside the project, not into the cache, so the file is yours to edit and can outlive a cache wipe. It attaches the captions only with --attach; otherwise you get the SRT and its word count and can review it first.

Silence is not a failure: a recording with no speech returns {"words":0,"speech":false} with an asr_no_speech warning.

​

Providers and keys

Keys never go in splice.json and never in argv.

echo "$GEMINI_API_KEY" | splice config set gemini.api_key --stdin
splice config set deepgram.model nova-3
splice config set whisper.program /path/to/whisper-cli
splice config set whisper.model /path/to/ggml-small.en.bin
splice config list

• gemini and deepgram are hosted; whisper runs a local binary.
• An environment variable beats the config file for the same provider.
• config list reports whether a key is set, from which source, and a fingerprint — never the key itself.

​

Burn them in

splice caption captions.srt

splice text and splice caption share one engine (libass). That is why a title and a subtitle look consistent, and why a build without libass cannot do either.

​

Fixing the words

captions.srt is a normal SRT. Edit it, then re-run splice caption. The render cache is keyed on the file’s content, so changing it invalidates only the burn-in step.

Timing lives in the SRT, not the document. If the transcription is right but the timing is not, edit the SRT rather than asking the provider again.