{ "schemaVersion": "1.0", "item": { "slug": "speechall-cli", "name": "Speechall command-line tool for fast speech-to-text transcription using multiple providers", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/atacan/speechall-cli", "canonicalUrl": "https://clawhub.ai/atacan/speechall-cli", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/speechall-cli", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=speechall-cli", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "slug": "speechall-cli", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-09T07:34:07.446Z", "expiresAt": "2026-05-16T07:34:07.446Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=speechall-cli", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=speechall-cli", "contentDisposition": "attachment; filename=\"speechall-cli-0.1.1.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "speechall-cli" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/speechall-cli" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/speechall-cli", "agentPageUrl": "https://openagent3.xyz/skills/speechall-cli/agent", "manifestUrl": "https://openagent3.xyz/skills/speechall-cli/agent.json", "briefUrl": "https://openagent3.xyz/skills/speechall-cli/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "speechall-cli", "body": "CLI for speech-to-text transcription via the Speechall API. Supports multiple providers (OpenAI, Deepgram, AssemblyAI, Google, Gemini, Groq, ElevenLabs, Cloudflare, and more)." }, { "title": "Homebrew (macOS and Linux)", "body": "brew install Speechall/tap/speechall\n\nWithout Homebrew: Download the binary for your platform from https://github.com/Speechall/speechall-cli/releases and place it on your PATH." }, { "title": "Verify", "body": "speechall --version" }, { "title": "Authentication", "body": "An API key is required. Provide it via environment variable (preferred) or flag:\n\nexport SPEECHALL_API_KEY=\"your-key-here\"\n# or\nspeechall --api-key \"your-key-here\" audio.wav\n\nThe user can create an API key on https://speechall.com/console/api-keys" }, { "title": "transcribe (default)", "body": "Transcribe an audio or video file. This is the default subcommand — speechall audio.wav is equivalent to speechall transcribe audio.wav.\n\nspeechall [options]\n\nOptions:\n\nFlagDescriptionDefault--model STT model identifieropenai.gpt-4o-mini-transcribe--language Language code (e.g. en, tr, de)API default (auto-detect)--output-format Output format (text, json, verbose_json, srt, vtt)API default--diarizationEnable speaker diarizationoff--speakers-expected Expected number of speakers (use with --diarization)—--no-punctuationDisable automatic punctuation—--temperature <0.0-1.0>Model temperature—--initial-prompt Text prompt to guide model style—--custom-vocabulary Terms to boost recognition (repeatable)—--ruleset-id Replacement ruleset UUID—--api-key API key (overrides SPEECHALL_API_KEY env var)—\n\nExamples:\n\n# Basic transcription\nspeechall interview.mp3\n\n# Specific model and language\nspeechall call.wav --model deepgram.nova-2 --language en\n\n# Speaker diarization with SRT output\nspeechall meeting.wav --diarization --speakers-expected 3 --output-format srt\n\n# Custom vocabulary for domain-specific terms\nspeechall medical.wav --custom-vocabulary \"myocardial\" --custom-vocabulary \"infarction\"\n\n# Transcribe a video file (macOS extracts audio automatically)\nspeechall presentation.mp4" }, { "title": "models", "body": "List available speech-to-text models. Outputs JSON to stdout. Filters combine with AND logic.\n\nspeechall models [options]\n\nFilter flags:\n\nFlagDescription--provider Filter by provider (e.g. openai, deepgram)--language Filter by supported language (tr matches tr, tr-TR, tr-CY)--diarizationOnly models supporting speaker diarization--srtOnly models supporting SRT output--vttOnly models supporting VTT output--punctuationOnly models supporting automatic punctuation--streamableOnly models supporting real-time streaming--vocabularyOnly models supporting custom vocabulary\n\nExamples:\n\n# List all available models\nspeechall models\n\n# Models from a specific provider\nspeechall models --provider deepgram\n\n# Models that support Turkish and diarization\nspeechall models --language tr --diarization\n\n# Pipe to jq for specific fields\nspeechall models --provider openai | jq '.[].identifier'" }, { "title": "Tips", "body": "On macOS, video files (.mp4, .mov, etc.) are automatically converted to audio before upload.\nOn Linux, pass audio files directly (.wav, .mp3, .m4a, .flac, etc.).\nOutput goes to stdout. Redirect to save: speechall audio.wav > transcript.txt\nErrors go to stderr, so piping stdout is safe.\nRun speechall --help, speechall transcribe --help, or speechall models --help to see all valid enum values for model identifiers, language codes, and output formats." } ], "body": "speechall-cli\n\nCLI for speech-to-text transcription via the Speechall API. Supports multiple providers (OpenAI, Deepgram, AssemblyAI, Google, Gemini, Groq, ElevenLabs, Cloudflare, and more).\n\nInstallation\nHomebrew (macOS and Linux)\nbrew install Speechall/tap/speechall\n\n\nWithout Homebrew: Download the binary for your platform from https://github.com/Speechall/speechall-cli/releases and place it on your PATH.\n\nVerify\nspeechall --version\n\nAuthentication\n\nAn API key is required. Provide it via environment variable (preferred) or flag:\n\nexport SPEECHALL_API_KEY=\"your-key-here\"\n# or\nspeechall --api-key \"your-key-here\" audio.wav\n\n\nThe user can create an API key on https://speechall.com/console/api-keys\n\nCommands\ntranscribe (default)\n\nTranscribe an audio or video file. This is the default subcommand — speechall audio.wav is equivalent to speechall transcribe audio.wav.\n\nspeechall [options]\n\n\nOptions:\n\nFlag\tDescription\tDefault\n--model \tSTT model identifier\topenai.gpt-4o-mini-transcribe\n--language \tLanguage code (e.g. en, tr, de)\tAPI default (auto-detect)\n--output-format \tOutput format (text, json, verbose_json, srt, vtt)\tAPI default\n--diarization\tEnable speaker diarization\toff\n--speakers-expected \tExpected number of speakers (use with --diarization)\t—\n--no-punctuation\tDisable automatic punctuation\t—\n--temperature <0.0-1.0>\tModel temperature\t—\n--initial-prompt \tText prompt to guide model style\t—\n--custom-vocabulary \tTerms to boost recognition (repeatable)\t—\n--ruleset-id \tReplacement ruleset UUID\t—\n--api-key \tAPI key (overrides SPEECHALL_API_KEY env var)\t—\n\nExamples:\n\n# Basic transcription\nspeechall interview.mp3\n\n# Specific model and language\nspeechall call.wav --model deepgram.nova-2 --language en\n\n# Speaker diarization with SRT output\nspeechall meeting.wav --diarization --speakers-expected 3 --output-format srt\n\n# Custom vocabulary for domain-specific terms\nspeechall medical.wav --custom-vocabulary \"myocardial\" --custom-vocabulary \"infarction\"\n\n# Transcribe a video file (macOS extracts audio automatically)\nspeechall presentation.mp4\n\nmodels\n\nList available speech-to-text models. Outputs JSON to stdout. Filters combine with AND logic.\n\nspeechall models [options]\n\n\nFilter flags:\n\nFlag\tDescription\n--provider \tFilter by provider (e.g. openai, deepgram)\n--language \tFilter by supported language (tr matches tr, tr-TR, tr-CY)\n--diarization\tOnly models supporting speaker diarization\n--srt\tOnly models supporting SRT output\n--vtt\tOnly models supporting VTT output\n--punctuation\tOnly models supporting automatic punctuation\n--streamable\tOnly models supporting real-time streaming\n--vocabulary\tOnly models supporting custom vocabulary\n\nExamples:\n\n# List all available models\nspeechall models\n\n# Models from a specific provider\nspeechall models --provider deepgram\n\n# Models that support Turkish and diarization\nspeechall models --language tr --diarization\n\n# Pipe to jq for specific fields\nspeechall models --provider openai | jq '.[].identifier'\n\nTips\nOn macOS, video files (.mp4, .mov, etc.) are automatically converted to audio before upload.\nOn Linux, pass audio files directly (.wav, .mp3, .m4a, .flac, etc.).\nOutput goes to stdout. Redirect to save: speechall audio.wav > transcript.txt\nErrors go to stderr, so piping stdout is safe.\nRun speechall --help, speechall transcribe --help, or speechall models --help to see all valid enum values for model identifiers, language codes, and output formats." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/atacan/speechall-cli", "publisherUrl": "https://clawhub.ai/atacan/speechall-cli", "owner": "atacan", "version": "0.1.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/speechall-cli", "downloadUrl": "https://openagent3.xyz/downloads/speechall-cli", "agentUrl": "https://openagent3.xyz/skills/speechall-cli/agent", "manifestUrl": "https://openagent3.xyz/skills/speechall-cli/agent.json", "briefUrl": "https://openagent3.xyz/skills/speechall-cli/agent.md" } }