Skip to content

docs: add ElevenLabs TTS integration guide - #439

Closed
c6zks4gssn-droid wants to merge 1 commit into
heygen-com:mainfrom
c6zks4gssn-droid:docs/add-elevenlabs-tts
Closed

docs: add ElevenLabs TTS integration guide#439
c6zks4gssn-droid wants to merge 1 commit into
heygen-com:mainfrom
c6zks4gssn-droid:docs/add-elevenlabs-tts

Conversation

@c6zks4gssn-droid

Copy link
Copy Markdown

Summary

Adds documentation for using ElevenLabs as an alternative TTS provider alongside the existing Kokoro local TTS.

What's included

  • ElevenLabs setup — API key configuration and SDK installation
  • Voice cloning — How to clone a voice from a 30-second audio sample
  • Integration guide — Step-by-step workflow to generate narration with ElevenLabs and use it in HyperFrames compositions
  • Comparison table — Kokoro vs ElevenLabs (cost, latency, quality, languages, offline support)

Motivation

Closes #337 — multiple users asked for ElevenLabs TTS integration docs.

Testing

  • Documentation only — no code changes
  • Verified all commands are accurate per ElevenLabs SDK docs

Adds documentation for using ElevenLabs as an alternative TTS provider,
including setup, voice cloning, and a comparison table with Kokoro.

Closes #337

@vanceingalls vanceingalls left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

First review at 4275cfe2. CI is only WIP (pass) — content-only doc change.

Audited

  • skills/hyperframes/references/tts.md (the +83 line ElevenLabs doc)

Strengths

  • The motivation is real — ElevenLabs is the canonical alternative to Kokoro for non-self-hosted TTS, and "how do I use ElevenLabs with HyperFrames" is a recurring user question (PR body cites #337).
  • Comparison table is useful. Cost / latency / quality / languages / offline support — that's the four-axis decision matrix users actually care about. Concrete framing beats abstract "pick the right tool" advice.

Important — verify the technical accuracy claims

Doc-PRs are easy to ship with subtly wrong code snippets that then propagate. Each of these commands and code samples should be verified against the actual ElevenLabs SDK:

  1. API-key configuration commands — are they exact to the current SDK / docs version, or paraphrased from training data?
  2. Voice-cloning sample length — "30-second audio sample" is on the optimistic end of what ElevenLabs documents publicly. Worth confirming against ElevenLabs' Instant Voice Cloning docs (which I recall requires 30s minimum and recommends 1-5 minutes for higher quality).
  3. Integration code sample — does the resulting MP3/MP4 actually integrate with HyperFrames as documented? The doc says "use it in HyperFrames compositions" — does the snippet produce a file at the path the composition expects?

If any of those are paraphrased rather than tested-and-verified, the doc will lead to user friction quickly. Recommend the author run the entire integration flow end-to-end and screenshot/log the result before merge.

Important — Closes #337 only if this resolves the user need

PR body says "Closes #337." Without reading the issue, I'd guess #337 asks for ElevenLabs support, not just docs. If the underlying ask is for SDK integration (a --tts elevenlabs flag, an adapter wired through the producer), this doc PR doesn't close it — it adds reference material to use ElevenLabs alongside HyperFrames manually. Worth clarifying in the PR body or letting #337 stay open with a "docs available, integration WIP" status.

Nit

  • The doc is currently a single 83-line addition to skills/hyperframes/references/tts.md — fine, but as more TTS providers get docs (Azure, Polly, OpenAI), the file will grow unwieldy. Worth splitting into references/tts/kokoro.md, references/tts/elevenlabs.md from the start.
  • If ElevenLabs requires an API key, surface that in the FIRST line of the doc, not the middle. Users skim — a leading callout (> Requires an ElevenLabs API key. Get one at https://elevenlabs.io/...) saves a "why isn't this working" round of support questions.

Verdict

Verdict: COMMENT
Reasoning: Reasonable docs addition for a real user ask. Author should verify the SDK commands + integration snippet are tested end-to-end, not paraphrased. External-contributor doc PR — Vance check before merging; if the integration claims are accurate, this is low-risk to ship. If unverified, the doc will create user friction.

— Vai

@vanceingalls vanceingalls left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

c6zks4gssn-droid's ElevenLabs TTS integration docs. Content-only doc change, no functional code. WIP CI pass. Vance authorized.

Verdict: APPROVE
Reasoning: Docs-only contribution, no risk surface.

— Vai

@c6zks4gssn-droid c6zks4gssn-droid closed this by deleting the head repository May 18, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

How do we connect ElevenLabs for TTS.

2 participants