repositories
loading repo index
repositories
loading repo index
repository
loading code, commits, and activity
public Clawd ADK gateway launch mirror
stars
latest
clone command
git clone gitlawb://did:key:z6Mkq5mY...iFZ5/my-project-publ...git clone gitlawb://did:key:z6Mkq5mY.../my-project-publ...2fa351d6docs: add automaton and perps launch sources16d ago| #1 | --- |
| #2 | name: sag |
| #3 | description: ElevenLabs text-to-speech with mac-style say UX. |
| #4 | homepage: https://sag.sh |
| #5 | metadata: {"clawdbot":{"emoji":"🗣️","requires":{"bins":["sag"],"env":["ELEVENLABS_API_KEY"]},"primaryEnv":"ELEVENLABS_API_KEY","install":[{"id":"brew","kind":"brew","formula":"steipete/tap/sag","bins":["sag"],"label":"Install sag (brew)"}]}} |
| #6 | --- |
| #7 | |
| #8 | # sag |
| #9 | |
| #10 | Use `sag` for ElevenLabs TTS with local playback. |
| #11 | |
| #12 | API key (required) |
| #13 | - `ELEVENLABS_API_KEY` (preferred) |
| #14 | - `SAG_API_KEY` also supported by the CLI |
| #15 | |
| #16 | Quick start |
| #17 | - `sag "Hello there"` |
| #18 | - `sag speak -v "Roger" "Hello"` |
| #19 | - `sag voices` |
| #20 | - `sag prompting` (model-specific tips) |
| #21 | |
| #22 | Model notes |
| #23 | - Default: `eleven_v3` (expressive) |
| #24 | - Stable: `eleven_multilingual_v2` |
| #25 | - Fast: `eleven_flash_v2_5` |
| #26 | |
| #27 | Pronunciation + delivery rules |
| #28 | - First fix: respell (e.g. "key-note"), add hyphens, adjust casing. |
| #29 | - Numbers/units/URLs: `--normalize auto` (or `off` if it harms names). |
| #30 | - Language bias: `--lang en|de|fr|...` to guide normalization. |
| #31 | - v3: SSML `<break>` not supported; use `[pause]`, `[short pause]`, `[long pause]`. |
| #32 | - v2/v2.5: SSML `<break time="1.5s" />` supported; `<phoneme>` not exposed in `sag`. |
| #33 | |
| #34 | v3 audio tags (put at the entrance of a line) |
| #35 | - `[whispers]`, `[shouts]`, `[sings]` |
| #36 | - `[laughs]`, `[starts laughing]`, `[sighs]`, `[exhales]` |
| #37 | - `[sarcastic]`, `[curious]`, `[excited]`, `[crying]`, `[mischievously]` |
| #38 | - Example: `sag "[whispers] keep this quiet. [short pause] ok?"` |
| #39 | |
| #40 | Voice defaults |
| #41 | - `ELEVENLABS_VOICE_ID` or `SAG_VOICE_ID` |
| #42 | |
| #43 | Confirm voice + speaker before long output. |
| #44 | |
| #45 | ## Chat voice responses |
| #46 | |
| #47 | When Peter asks for a "voice" reply (e.g., "crazy scientist voice", "explain in voice"), generate audio and send it: |
| #48 | |
| #49 | ```bash |
| #50 | # Generate audio file |
| #51 | sag -v Clawd -o /tmp/voice-reply.mp3 "Your message here" |
| #52 | |
| #53 | # Then include in reply: |
| #54 | # MEDIA:/tmp/voice-reply.mp3 |
| #55 | ``` |
| #56 | |
| #57 | Voice character tips: |
| #58 | - Crazy scientist: Use `[excited]` tags, dramatic pauses `[short pause]`, vary intensity |
| #59 | - Calm: Use `[whispers]` or slower pacing |
| #60 | - Dramatic: Use `[sings]` or `[shouts]` sparingly |
| #61 | |
| #62 | Default voice for Clawd: `lj2rcrvANS3gaWWnczSX` (or just `-v Clawd`) |
| #63 |