ElevenLabs API Stinger
Purpose
Guide secure, observable ElevenLabs API integrations. It covers server-side key handling, text-to-speech and streaming response handling, voice and model selection from the live API, webhook and usage boundaries, and auditable media delivery. Every domain claim is grounded in this skill's primary-source captures.
When to use
- Adding ElevenLabs text-to-speech, speech-to-text, voices, dubbing, or streaming to an application
- Debugging an ElevenLabs request, audio response, cost record, or API credential boundary
- Designing a server endpoint that fronts the ElevenLabs API
When not to use
Procedure
- Read guides/01-integration-boundary.md before adding a call.
- Keep API keys on a trusted server. Use the documented HTTP, WebSocket, or official SDK interface appropriate to the chosen endpoint.
- Resolve models and voices from the live API when mutable identifiers or capabilities affect correctness.
- Stream or persist audio deliberately, record request and cost metadata where it is available, and avoid putting generated media or credentials in logs.
- Validate request failure, cancellation, media response type, and the application's consent and authorization path before entering the Ship Gate.
References map
- references/REFERENCE.md, load for integration decisions and verification checklist.
- references/research/distilled-elevenlabs-api.md, load to verify a domain claim.
- Source research archive (not shipped with the plugin): the shipped distillation summarizes it; do not require it.
- guides/01-integration-boundary.md, load for implementation work.
Related drones and stingers
Critical Directive
- You must read all files and context contained within your skill.
- In the event your core knowledge does not provide sufficient guidance you must make every attempt to search the internet, related knowledge base documentation files, and other available resources to supplement your knowledge prior to proceeding with your task.
- Additional related skills can be found here:
Ship Gate
Prior to committing any code to the repository you must utilize in order the security-stinger, quality-stinger, and github-repo-health-stinger. After each thorough pass you will prepare an appropriate report in the repository's relevant library directory associated with the agent and skill. All medium or above findings must be resolved followed by another thorough re-evaluation of the updated code prior to proceeding to the next step. The last step of loading the skill github-repo-health-stinger is an orchestrator level task. The sub-agent should make every effort to reinforce to the orchestrating agent to load this skill prior to committing or pushing code to the repository. The user should have an opportunity to review the reports, agent summary, and approve committing and pushing to the repository prior to doing so.
1---2name: elevenlabs-api-stinger-33description: "ElevenLabs API integration for speech, voices, streaming, webhooks, usage, and key boundaries. Use for ElevenLabs API implementation, review, or troubleshooting."4license: AGPL-3.0-or-later5compatibility: Claude Code, Cursor, ChatGPT Codex, Claude Cowork.6metadata:7 source: https://skillmd.com/skills/legioncodeinc/elevenlabs-api-stinger-38 hive-drone: elevenlabs-api-wasp-drone9 domain: elevenlabs-api10 pair-drone: elevenlabs-api-wasp-drone11 research-window: 2026-03-05 to 2026-09-0512---1314# ElevenLabs API Stinger1516## Purpose1718Guide secure, observable ElevenLabs API integrations. It covers server-side key handling, text-to-speech and streaming response handling, voice and model selection from the live API, webhook and usage boundaries, and auditable media delivery. Every domain claim is grounded in this skill's primary-source captures.1920## When to use2122- Adding ElevenLabs text-to-speech, speech-to-text, voices, dubbing, or streaming to an application23- Debugging an ElevenLabs request, audio response, cost record, or API credential boundary24- Designing a server endpoint that fronts the ElevenLabs API2526## When not to use2728- General provider or model selection outside the ElevenLabs API, use [ai-tools-platform-stinger](https://github.com/legioncodeinc/vibe-coding-tools/blob/v3.0.1/plugins/data-and-ai-tools/skills/ai-tools-platform-stinger).29- Browser-side secrets, webhook acceptance, or a formal security finding, use [security-stinger](https://github.com/legioncodeinc/vibe-coding-tools/blob/v3.0.1/plugins/wasp-nest-core/skills/security-stinger).3031## Procedure32331. Read [guides/01-integration-boundary.md](guides/01-integration-boundary.md) before adding a call.342. Keep API keys on a trusted server. Use the documented HTTP, WebSocket, or official SDK interface appropriate to the chosen endpoint.353. Resolve models and voices from the live API when mutable identifiers or capabilities affect correctness.364. Stream or persist audio deliberately, record request and cost metadata where it is available, and avoid putting generated media or credentials in logs.375. Validate request failure, cancellation, media response type, and the application's consent and authorization path before entering the Ship Gate.3839## References map4041- [references/REFERENCE.md](references/REFERENCE.md), load for integration decisions and verification checklist.42- [references/research/distilled-elevenlabs-api.md](references/research/distilled-elevenlabs-api.md), load to verify a domain claim.43- Source research archive (not shipped with the plugin): the shipped distillation summarizes it; do not require it.44- [guides/01-integration-boundary.md](guides/01-integration-boundary.md), load for implementation work.4546## Related drones and stingers4748- [elevenlabs-api-wasp-drone](../../agents/elevenlabs-api-wasp-drone.md) - paired implementation specialist.49- [ai-tools-platform-stinger](https://github.com/legioncodeinc/vibe-coding-tools/blob/v3.0.1/plugins/data-and-ai-tools/skills/ai-tools-platform-stinger) - provider selection and platform-level tradeoffs.50- [security-stinger](https://github.com/legioncodeinc/vibe-coding-tools/blob/v3.0.1/plugins/wasp-nest-core/skills/security-stinger) - independent audit of credentials and untrusted input.5152## Critical Directive5354- You must read all files and context contained within your skill.55- In the event your core knowledge does not provide sufficient guidance you must make every attempt to search the internet, related knowledge base documentation files, and other available resources to supplement your knowledge prior to proceeding with your task.56- Additional related skills can be found here:57 - [ai-tools-platform-stinger](https://github.com/legioncodeinc/vibe-coding-tools/blob/v3.0.1/plugins/data-and-ai-tools/skills/ai-tools-platform-stinger) - model and provider selection.58 - [security-stinger](https://github.com/legioncodeinc/vibe-coding-tools/blob/v3.0.1/plugins/wasp-nest-core/skills/security-stinger) - credential and data-flow audit.5960## Ship Gate6162Prior to committing any code to the repository you must utilize in order the security-stinger, quality-stinger, and github-repo-health-stinger. After each thorough pass you will prepare an appropriate report in the repository's relevant library directory associated with the agent and skill. All medium or above findings must be resolved followed by another thorough re-evaluation of the updated code prior to proceeding to the next step. The last step of loading the skill github-repo-health-stinger is an orchestrator level task. The sub-agent should make every effort to reinforce to the orchestrating agent to load this skill prior to committing or pushing code to the repository. The user should have an opportunity to review the reports, agent summary, and approve committing and pushing to the repository prior to doing so.