#Give me brief summary on all names, tools, uses, pretty much new on this. And how to be freelance o

1 messages · Page 1 of 1 (latest)

nova arrowBOT
#
AI-generated Answer for sanesa

Here’s a concise, docs-only orientation to ElevenLabs and how to earn as a freelancer on the platform.

What ElevenLabs offers (names, tools, uses)

  • Creative Platform (web studio and APIs)
    • Text to Speech: convert text to natural speech; main models include Multilingual v2 (quality/29+ languages), Flash v2.5 (ultra‑low latency), Turbo v2.5 (quality/low latency), and Eleven v3 (Alpha, most expressive; not for commercial use under Beta Services). API uses the xi-api-key header. (elevenlabs.io)
    • Voices (Voice Lab): create and manage voices via Instant Voice Cloning, Professional Voice Cloning (PVC), Voice Design (prompt-based), and Voice Remixing (alpha) to transform voices you own. (elevenlabs.io)
    • Voice Library (marketplace): browse and add shared voices; only Professional Voice Clones can be shared/monetized. Filters include language/accent, age, notice period, live moderation, custom rate. (help.elevenlabs.io)
    • Dubbing: translate/retain speaker identity across 32 languages; use Dubbing Studio (UI) or API. UI: up to 500 MB/45 min; API: up to 1 GB/2.5 h. (elevenlabs.io)
    • Voice Changer (speech‑to‑speech): convert a source recording into another voice while preserving performance; API endpoint /v1/speech-to-speech/:voice_id. (help.elevenlabs.io)
    • Speech to Text (Scribe): batch STT (Scribe v2) and realtime STT (~150 ms, Scribe v2 Realtime) in 90+ languages; supports diarization, timestamps, keyterm prompting, entity detection. (elevenlabs.io)
    • Sound Effects: generate SFX (and musical elements) from text with duration/looping controls. (elevenlabs.io)
    • Eleven Music: generate studio‑grade music (with vocals or instrumental) and edit sections; API available for paid plans; broad commercial use per Music Terms. (help.elevenlabs.io)
    • Studio (Projects): long‑form production workflow (audiobooks, podcasts, articles) with export; integrates with Audio Native. (elevenlabs.io)
    • Audio Native: embeddable player that auto‑voices webpages or embeds pre‑generated project audio; includes analytics. (elevenlabs.io)
    • AI Speech Classifier: free tool to detect if audio was generated by ElevenLabs (notes reduced reliability on v3). (elevenlabs.io)
  • Agents Platform (build conversational voice agents)
    • Configure voice/chat agents, connect tools/APIs (client, server, MCP), deploy via web/telephony/Twilio/SIP, and monitor with testing/analytics. Uses STT + your LLM + low‑latency TTS + turn‑taking. SDKs and WebSocket API provided. (elevenlabs.io)
  • Mobile
    • ElevenLabs app / ElevenReader: iOS/Android app to listen to articles, PDFs, ePubs in 32 languages; some features like GenFM podcasts on iOS. (help.elevenlabs.io)

Key model names (by ID)

  • eleven_multilingual_v2 (TTS), eleven_flash_v2_5 (TTS, ultra‑fast), eleven_turbo_v2_5 (TTS), eleven_v3 (Alpha, TTS), plus STS models (e.g., eleven
digital cove
#

What is api

nova arrowBOT
#
AI-generated Answer for sanesa

  • In ElevenLabs terms, the API is a set of HTTP and WebSocket endpoints that let you programmatically use ElevenLabs’ audio models (for example Text to Speech and Speech to Text) from your app or service. You can call it directly over HTTP or via realtime WebSockets, and there are official Python and Node.js SDKs to simplify this. (elevenlabs.io)

  • Authentication: every request must include your secret xi-api-key in the request headers. Keys can be scoped to limit accessible endpoints and assigned credit quotas; never expose them client‑side. (elevenlabs.io)

  • Examples of what the API does:

    • Convert text into speech with POST /v1/text-to-speech/:voice_id (returns audio). (elevenlabs.io)
    • Stream text-to-speech over WebSocket for low‑latency generation. (elevenlabs.io)
    • Stream speech-to-text (Scribe Realtime) over WebSocket or use REST for transcription. (elevenlabs.io)

  • Where to learn more: see the API Reference and Developer quickstart in the official docs; the Help Center also points you to these resources and the Discord community. (elevenlabs.io)

Sources:
Introduction | ElevenLabs Documentation
API Authentication | ElevenLabs Documentation
Create speech | ElevenLabs Documentation
WebSocket | ElevenLabs Documentation
Realtime | ElevenLabs Documentation
Introduction | ElevenLabs Documentation

digital cove
#

How to start freelance on elevenlab

nova arrowBOT
#
AI-generated Answer for sanesa

Below are the two official, supported ways to monetize your work with ElevenLabs. I’m only using information from the ElevenLabs Help Center and docs; each statement is cited.

Path A — Earn on ElevenLabs as a voice actor (Voice Library payouts)

  • Create a Professional Voice Clone (PVC) of your own voice. PVC creation is available on Creator plan and above; Free/Starter don’t have PVC slots. Recommended: upload ~2 hours of clean audio; you can only clone your own voice. (help.elevenlabs.io)
  • Share your PVC in the Voice Library after verification and review. Only Professional Voice Clones can be shared; Instant Voice Clones and Voice Design voices cannot. (help.elevenlabs.io)
  • Configure Voice Actor Payouts. Payouts are calculated from paid-user generations, default rate depends on the notice period you set, and payments are sent via Stripe. Weekly payouts start once you reach the $10 threshold; set up Stripe Connect to receive them. Maintaining a paid subscription (Starter or above) is required to receive payments. (help.elevenlabs.io)
  • Understand Voice Library controls and lifecycle. Notice periods ensure clients can keep using a voice for a defined time after you withdraw it; Live Moderation can block restricted use. (help.elevenlabs.io)

Path B — Freelance off‑platform using ElevenLabs tools (client work)

  • Use a paid plan for commercial work. All paid plans include a commercial license for non‑beta services, provided you hold the necessary rights; the free plan is non‑commercial and requires attribution if you share content. (help.elevenlabs.io)
  • Produce and deliver assets:
    • Text to Speech via API (create speech endpoint) for programmatic pipelines. (elevenlabs.io)
    • Studio for long‑form narration and video voiceovers; you can import scripts/files and export MP3 or WAV for delivery. (help.elevenlabs.io)
    • Dubbing to translate/dub audio or video; Dubbing Studio (the pro editor) is on paid tiers, with costs shown per minute and per language. (help.elevenlabs.io)
    • Supported output formats (e.g., MP3/WAV; higher bitrates on higher tiers) are documented. (help.elevenlabs.io)
  • Using voices:
    • Default voices are available to all accounts. (help.elevenlabs.io)
    • Voice Library voices may have notice periods, Live Moderation, or credit multipliers; some are unavailable on the free plan. Factor this into project pricing/quotes. (help.elevenlabs.io)

Getting started (API and integrations)

  • Create an API key and follow the “Get started” guide, then integrate the Text‑to‑Speech or Realtime endpoints in your stack.
digital cove
#

Starting on elevenlabs