--- title: Use ElevenLabs in WorkBuddy via RunAPI — TTS MCP Guide | RunAPI description: Add ElevenLabs text-to-speech, speech-to-text, and audio isolation to WorkBuddy through the RunAPI MCP server. One key, 29 languages, async tasks. url: https://runapi.ai/workbuddy-elevenlabs.md canonical: https://runapi.ai/workbuddy-elevenlabs locale: en site: RunAPI image: https://runapi.ai/assets/opengraph-bfaaa0f0.png alternates: en: https://runapi.ai/workbuddy-elevenlabs zh-CN: https://runapi.ai/zh-CN/workbuddy-elevenlabs es: https://runapi.ai/es/workbuddy-elevenlabs ja: https://runapi.ai/ja/workbuddy-elevenlabs de: https://runapi.ai/de/workbuddy-elevenlabs fr: https://runapi.ai/fr/workbuddy-elevenlabs pt-BR: https://runapi.ai/pt-BR/workbuddy-elevenlabs ko: https://runapi.ai/ko/workbuddy-elevenlabs it: https://runapi.ai/it/workbuddy-elevenlabs nl: https://runapi.ai/nl/workbuddy-elevenlabs pl: https://runapi.ai/pl/workbuddy-elevenlabs tr: https://runapi.ai/tr/workbuddy-elevenlabs zh-TW: https://runapi.ai/zh-TW/workbuddy-elevenlabs zh-HK: https://runapi.ai/zh-HK/workbuddy-elevenlabs ar: https://runapi.ai/ar/workbuddy-elevenlabs x-default: https://runapi.ai/workbuddy-elevenlabs model: elevenlabs --- > HTML version: https://runapi.ai/workbuddy-elevenlabs > Site index for agents: https://runapi.ai/llms.txt # Use ElevenLabs in WorkBuddy. ElevenLabs provides six audio endpoints through RunAPI — turbo-v2.5 TTS with sub-second latency, multilingual-v2 covering 29 languages, dialogue-v3 for multi-speaker conversations, sound effects, speech-to-text transcription, and vocal isolation. Add RunAPI as an MCP server once, and the WorkBuddy agent can call any of them with the same key. - [Get API Key](https://runapi.ai/login) - [Read the docs](https://runapi.ai/docs/guides) one MCP server · six audio endpoints · per-character billing ### Prompt ```text Using the runapi MCP server, generate speech audio with ElevenLabs. Requirements: - Call the ElevenLabs text_to_speech tool exposed by the runapi MCP server. - Set model to "text-to-speech-turbo-v2.5". - Text: "Welcome to RunAPI. This audio was generated from WorkBuddy." - Set speed to 1.0, stability to 0.5, similarity_boost to 0.75. - The task is async — keep polling until the status is "completed", then give me the audio URL. ``` ### MCP config ```bash { "mcp_servers": { "runapi": { "url": "https://runapi.ai/mcp", "transport": "streamable_http", "headers": { "Authorization": "Bearer $RUNAPI_API_KEY" } } } } ``` ### Response ```json { "task_id": "tsk_abc123", "status": "completed", "model": "text-to-speech-turbo-v2.5", "output": { "audio_url": "https://media.runapi.ai/outputs/tsk_abc123.mp3", "characters_billed": 62 } } ``` ## Use ElevenLabs in WorkBuddy in three steps 1. **Add RunAPI as an MCP server** - Set RUNAPI_API_KEY in the environment that launches WorkBuddy, then register an MCP server named runapi pointing at https://runapi.ai/mcp over streamable HTTP. All six ElevenLabs endpoints — TTS, STT, dialogue, sound effects, and audio isolation — become callable tools behind one key. `export RUNAPI_API_KEY=runapi_xxx # MCP server: runapi → https://runapi.ai/mcp ` 2. **Ask the agent to speak your text** - Prompt WorkBuddy with the text you want spoken and name the model — text-to-speech-turbo-v2.5 for low-latency English, or text-to-speech-multilingual-v2 with a voice ID and language_code for 29 languages. Mention speed, stability, or similarity_boost when you want to tune the voice. `model: text-to-speech-turbo-v2.5` 3. **Receive the audio in the workbench** - The task runs async. The workbench agent polls through the MCP tool until the status is completed, then posts the output audio URL back into the conversation, along with the character count that was billed. `"status": "completed"` ## ElevenLabs text_to_speech parameters | Parameter | Type | Description | | --- | --- | --- | | `model` | `string` | Required. text-to-speech-turbo-v2.5 (low latency) or text-to-speech-multilingual-v2 (29 languages). | | `text` | `string` | Required. The text to convert to speech. Max 5000 characters. | | `voice` | `string` | ElevenLabs voice ID. Required for multilingual-v2. Turbo-v2.5 uses a default voice if omitted. | | `speed` | `float` | Optional. Playback speed multiplier. Range 0.7 to 1.2. | | `stability` | `float` | Optional. Voice consistency. Range 0.0 to 1.0. Lower values add expressiveness. | | `similarity_boost` | `float` | Optional. Voice similarity enforcement. Range 0.0 to 1.0. | ## What is ElevenLabs on WorkBuddy? ElevenLabs is the go-to text-to-speech API for natural-sounding voice output. Through the RunAPI MCP server, the WorkBuddy agent gets access to turbo-v2.5 (sub-second latency for English), multilingual-v2 (29 languages), dialogue-v3 (multi-speaker conversations), sound effects generation, speech-to-text transcription, and vocal isolation. You can tune voice output with stability and similarity boost sliders to control how expressive or consistent the voice sounds — all from a plain-language prompt in the workbench. ## ElevenLabs use cases - **Audiobook and podcast narration** - Convert long-form text into spoken audio using consistent character voices. Ask the agent to keep stability high for narrator consistency and similarity boost close to the original profile across hours of content. - **Video dubbing into multiple languages** - Dub video content into 29 languages using multilingual-v2 with the same voice profile, producing localized versions that maintain the original speaker's vocal characteristics — all requested from the workbench conversation. - **Sound effects for video and game production** - Generate custom Foley sounds, ambient audio, and sound cues from text descriptions through the text_to_sound endpoint, replacing stock audio library searches with on-demand generation inside WorkBuddy. ## ElevenLabs + WorkBuddy questions ### Which ElevenLabs endpoints can WorkBuddy reach through RunAPI? Six of them — text_to_speech (turbo-v2.5 and multilingual-v2), text_to_dialogue (dialogue-v3 for multiple speakers), text_to_sound (sound effects), speech_to_text (transcription), and isolate_audio (vocal extraction). They all sit behind the same runapi MCP server and RUNAPI_API_KEY. ### What stability and similarity settings should I use for the most natural voice? Start with stability at 0.5 and similarity_boost at 0.75. Higher stability makes the voice more consistent but less expressive. For audiobooks, try stability 0.6-0.8. For conversational content, lower stability (0.3-0.5) adds natural variation. You can state these values in your WorkBuddy prompt. ### What is the difference between turbo-v2.5 and multilingual-v2? Turbo-v2.5 is optimized for low latency and English-first output -- it applies a default voice when none is specified. Multilingual-v2 supports 29 languages and requires an explicit voice ID and optional language_code. Turbo costs roughly half as much per character. ### How is ElevenLabs billed on RunAPI? Text-to-speech and dialogue endpoints are billed per character of input text. Speech-to-text is billed per minute of audio. Audio isolation is billed per task. Usage pools into the same RunAPI balance as every other model WorkBuddy calls — check the RunAPI pricing page for current rates. ### Can I use ElevenLabs dialogue-v3 for multi-speaker audio in WorkBuddy? Yes. Ask the agent to call the text_to_dialogue tool with model text-to-dialogue-v3, passing a dialogue array where each item has a text and a voice ID. The total text across all speakers must be under 5000 characters. - [WorkBuddy setup guide →](https://runapi.ai/workbuddy.md) - Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy. - [ElevenLabs on RunAPI →](https://runapi.ai/models/elevenlabs.md) - See all ElevenLabs variants, pricing, and API docs. ## Try ElevenLabs in WorkBuddy today. Get a free RunAPI key, add the MCP server to WorkBuddy, and ask the workbench agent to speak your text — six audio endpoints, one key, per-character billing. [Browse models →](https://runapi.ai/models.md) --- ## More from RunAPI - [Home](https://runapi.ai/.md) ### Product - [Model Catalog](https://runapi.ai/models.md) - [Pricing](https://runapi.ai/pricing.md) - [Providers](https://runapi.ai/models#all-models) ### Developers - [Documentation](https://runapi.ai/docs/guides) - [SDKs](https://runapi.ai/sdk.md) - [CLI](https://runapi.ai/cli.md) - [MCP Server](https://runapi.ai/mcp.md) - [x402](https://runapi.ai/x402.md) ### Guides - [Claude Code vs Cursor](https://runapi.ai/claude-code-vs-cursor.md) - [Cursor API Setup](https://runapi.ai/cursor-api-setup.md) - [RunAPI vs OpenRouter](https://runapi.ai/openrouter-alternative.md) ### Company - [Enterprise](https://runapi.ai/contact.md) - [Contact](https://runapi.ai/contact.md) ### Legal - [Terms](https://runapi.ai/terms.md) - [Privacy](https://runapi.ai/privacy.md) - [Site index for agents](https://runapi.ai/llms.txt) Contact: contact@runapi.ai ## Structured data ```json [ { "@context": "https://schema.org", "inLanguage": "en", "@type": "WebSite", "name": "RunAPI", "url": "https://runapi.ai/", "potentialAction": { "@type": "SearchAction", "target": { "@type": "EntryPoint", "urlTemplate": "https://runapi.ai/models?q={search_term_string}" }, "query-input": "required name=search_term_string" } }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "Organization", "name": "RunAPI", "url": "https://runapi.ai/", "logo": { "@type": "ImageObject", "url": "https://runapi.ai/icon.svg" }, "sameAs": [ "https://github.com/runapi-ai" ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "SoftwareApplication", "name": "RunAPI ElevenLabs for WorkBuddy", "applicationCategory": "DeveloperApplication", "description": "Add ElevenLabs text-to-speech, speech-to-text, and audio isolation to WorkBuddy through the RunAPI MCP server. One key, 29 languages, async tasks.", "url": "https://runapi.ai/workbuddy-elevenlabs" }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "Which ElevenLabs endpoints can WorkBuddy reach through RunAPI?", "acceptedAnswer": { "@type": "Answer", "text": "Six of them — text_to_speech (turbo-v2.5 and multilingual-v2), text_to_dialogue (dialogue-v3 for multiple speakers), text_to_sound (sound effects), speech_to_text (transcription), and isolate_audio (vocal extraction). They all sit behind the same runapi MCP server and RUNAPI_API_KEY." } }, { "@type": "Question", "name": "What stability and similarity settings should I use for the most natural voice?", "acceptedAnswer": { "@type": "Answer", "text": "Start with stability at 0.5 and similarity_boost at 0.75. Higher stability makes the voice more consistent but less expressive. For audiobooks, try stability 0.6-0.8. For conversational content, lower stability (0.3-0.5) adds natural variation. You can state these values in your WorkBuddy prompt." } }, { "@type": "Question", "name": "What is the difference between turbo-v2.5 and multilingual-v2?", "acceptedAnswer": { "@type": "Answer", "text": "Turbo-v2.5 is optimized for low latency and English-first output -- it applies a default voice when none is specified. Multilingual-v2 supports 29 languages and requires an explicit voice ID and optional language_code. Turbo costs roughly half as much per character." } }, { "@type": "Question", "name": "How is ElevenLabs billed on RunAPI?", "acceptedAnswer": { "@type": "Answer", "text": "Text-to-speech and dialogue endpoints are billed per character of input text. Speech-to-text is billed per minute of audio. Audio isolation is billed per task. Usage pools into the same RunAPI balance as every other model WorkBuddy calls — check the RunAPI pricing page for current rates." } }, { "@type": "Question", "name": "Can I use ElevenLabs dialogue-v3 for multi-speaker audio in WorkBuddy?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Ask the agent to call the text_to_dialogue tool with model text-to-dialogue-v3, passing a dialogue array where each item has a text and a voice ID. The total text across all speakers must be under 5000 characters." } } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "HowTo", "name": "How to use ElevenLabs in WorkBuddy via RunAPI", "description": "Add RunAPI as an MCP server in WorkBuddy, ask the workbench agent to speak your text with ElevenLabs, and receive the finished audio URL back in the conversation.", "step": [ { "@type": "HowToStep", "position": 1, "name": "Add RunAPI as an MCP server", "text": "Set RUNAPI_API_KEY in the environment that launches WorkBuddy, then register an MCP server named runapi pointing at https://runapi.ai/mcp over streamable HTTP. All six ElevenLabs endpoints — TTS, STT, dialogue, sound effects, and audio isolation — become callable tools behind one key.", "url": "https://runapi.ai/workbuddy-elevenlabs#how-step-1" }, { "@type": "HowToStep", "position": 2, "name": "Ask the agent to speak your text", "text": "Prompt WorkBuddy with the text you want spoken and name the model — text-to-speech-turbo-v2.5 for low-latency English, or text-to-speech-multilingual-v2 with a voice ID and language_code for 29 languages. Mention speed, stability, or similarity_boost when you want to tune the voice.", "url": "https://runapi.ai/workbuddy-elevenlabs#how-step-2" }, { "@type": "HowToStep", "position": 3, "name": "Receive the audio in the workbench", "text": "The task runs async. The workbench agent polls through the MCP tool until the status is completed, then posts the output audio URL back into the conversation, along with the character count that was billed.", "url": "https://runapi.ai/workbuddy-elevenlabs#how-step-3" } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://runapi.ai/" }, { "@type": "ListItem", "position": 2, "name": "RunAPI ElevenLabs for WorkBuddy", "item": "https://runapi.ai/workbuddy-elevenlabs" } ] } ] ```