{"id":"b42a8b5c-3156-46b9-92eb-2bfd49d98898","shortId":"52b3Y5","kind":"skill","title":"Self-host an OpenAI-compatible speech API for local transcription, translation, and TTS with Speaches","tagline":"Use Speaches when an agent stack expects OpenAI-style audio endpoints but you want a self-hosted speech backend for transcription, translation, and text-to-speech instead of a hosted API.","description":"# Self-host an OpenAI-compatible speech API for local transcription, translation, and TTS with Speaches\n\nUse Speaches when an agent stack expects OpenAI-style audio endpoints but you want a self-hosted speech backend for transcription, translation, and text-to-speech instead of a hosted API.\n\n## Prerequisites\n\nDocker or Python-based deployment environment, CPU or GPU runtime, supported speech models, and any client or agent stack that can call OpenAI-compatible audio endpoints.\n\n## Installation\n\nRequirements and caveats from upstream:\n- [Deployable via Docker Compose / Docker](https://speaches.ai/installation/)\n\nBasic usage or getting-started notes:\n- See the documentation for installation instructions and usage: [speaches.ai](https://speaches.ai/)\n- [Realtime API](https://speaches.ai/usage/realtime-api)\n\n- Source: https://github.com/speaches-ai/speaches\n- Extracted from upstream docs: https://raw.githubusercontent.com/speaches-ai/speaches/HEAD/README.md\n\n## Documentation\n\n- https://speaches.ai\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches/)","tags":["self","host","openai","compatible","speech","api","for","local","transcription","translation","and","tts"],"capabilities":["skill","source-agentskillexchange","skill-self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches","topic-agent-skills","topic-ai-agents","topic-ai-tools","topic-awesome-list","topic-claude-code","topic-codex","topic-cursor","topic-llm","topic-mcp","topic-npx-skills","topic-openclaw","topic-skills-catalog"],"categories":["skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/agentskillexchange/skills/self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add agentskillexchange/skills","source_repo":"https://github.com/agentskillexchange/skills","install_from":"skills.sh"}},"qualityScore":"0.454","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,186 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:12:23.979Z","embedding":null,"createdAt":"2026-05-18T13:19:16.903Z","updatedAt":"2026-05-18T19:12:23.979Z","lastSeenAt":"2026-05-18T19:12:23.979Z","tsv":"'/)':164 '/installation/)':145 '/skills/self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches/)':189 '/speaches-ai/speaches':173 '/speaches-ai/speaches/head/readme.md':180 '/usage/realtime-api)':169 'agent':22,73,122,184 'agentskillexchange.com':188 'agentskillexchange.com/skills/self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches/)':187 'api':9,51,60,102,166 'audio':28,79,130 'backend':38,89 'base':108 'basic':146 'call':126 'caveat':135 'client':120 'compat':7,58,129 'compos':141 'cpu':111 'deploy':109,138 'doc':177 'docker':104,140,142 'document':155,181 'endpoint':29,80,131 'environ':110 'exchang':186 'expect':24,75 'extract':174 'get':150 'getting-start':149 'github.com':172 'github.com/speaches-ai/speaches':171 'gpu':113 'host':3,36,50,54,87,101 'instal':132,157 'instead':47,98 'instruct':158 'local':11,62 'model':117 'note':152 'openai':6,26,57,77,128 'openai-compat':5,56,127 'openai-styl':25,76 'prerequisit':103 'python':107 'python-bas':106 'raw.githubusercontent.com':179 'raw.githubusercontent.com/speaches-ai/speaches/head/readme.md':178 'realtim':165 'requir':133 'runtim':114 'see':153 'self':2,35,53,86 'self-host':1,34,52,85 'skill':185 'skill-self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches' 'sourc':170,183 'source-agentskillexchange' 'speach':17,19,68,70 'speaches.ai':144,161,163,168,182 'speaches.ai/)':162 'speaches.ai/installation/)':143 'speaches.ai/usage/realtime-api)':167 'speech':8,37,46,59,88,97,116 'stack':23,74,123 'start':151 'style':27,78 'support':115 'text':44,95 'text-to-speech':43,94 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-tools' 'topic-awesome-list' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-llm' 'topic-mcp' 'topic-npx-skills' 'topic-openclaw' 'topic-skills-catalog' 'transcript':12,40,63,91 'translat':13,41,64,92 'tts':15,66 'upstream':137,176 'usag':147,160 'use':18,69 'via':139 'want':32,83","prices":[{"id":"239d0ea6-a132-4d1c-900b-1686a90c12fb","listingId":"b42a8b5c-3156-46b9-92eb-2bfd49d98898","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"agentskillexchange","category":"skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:19:16.903Z"}],"sources":[{"listingId":"b42a8b5c-3156-46b9-92eb-2bfd49d98898","source":"github","sourceId":"agentskillexchange/skills/self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches","isPrimary":false,"firstSeenAt":"2026-05-18T13:19:16.903Z","lastSeenAt":"2026-05-18T19:12:23.979Z"}],"details":{"listingId":"b42a8b5c-3156-46b9-92eb-2bfd49d98898","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches","github":{"repo":"agentskillexchange/skills","stars":8,"topics":["agent-skills","ai-agents","ai-tools","awesome-list","claude-code","codex","cursor","llm","mcp","npx-skills","openclaw","skills-catalog"],"license":"mit","html_url":"https://github.com/agentskillexchange/skills","pushed_at":"2026-05-18T19:02:17Z","description":"The open catalog of AI agent skills — 2,000+ security-scanned skills for Claude Code, Cursor, Codex, and more.","skill_md_sha":"743ac05ba2e604a62ce299c2d435f04128bb43fc","skill_md_path":"skills/self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Self-host an OpenAI-compatible speech API for local transcription, translation, and TTS with Speaches","description":"Use Speaches when an agent stack expects OpenAI-style audio endpoints but you want a self-hosted speech backend for transcription, translation, and text-to-speech instead of a hosted API."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches"},"updatedAt":"2026-05-18T19:12:23.979Z"}}