ElevenLabs
on Orq.ai
Use ElevenLabs’ AI voice and audio models through a single Orq.ai API. Route text‑to‑speech (TTS), voice cloning, and conversational audio workloads through Orq’s AI Router to add speech to your LLM apps, agents, and workflows.
Capabilities:
Chat
Speech
Models Supported:
scribe_v2
scribe_v1
eleven_flash_v2
eleven_flash_v2_5
eleven_multilingual_v2
Provider HQ:
ElevenLabs, with global operations and a primary presence in Europe and the United States.
Access ElevenLabs through Orq.ai’s AI Router
ElevenLabs provides high‑quality text‑to‑speech, voice cloning, and audio agents via the ElevenAPI, with multiple model families optimized for quality, latency, and multilingual support. These models cover use cases from real‑time voice agents and narration to batch audio generation and multimodal assistants.
[ Text‑to‑Speech] [ Voice Cloning] [ Conversational AI] [ Multilingual]Orq.ai supports major ElevenLabs TTS and voice models (such as Multilingual v2/v3 and Flash/Turbo variants), with availability depending on provider access, plan, and your workspace configuration.
ElevenLabs models available on Orq.ai
Model (example) | Type | Context / scope | Best for | Pricing tier (reference) |
|---|---|---|---|---|
Multilingual v2/v3 (Standard) | TTS / high‑quality audio | Character‑based (1 character ≈ 1 credit; see docs for limits per request) | High‑quality, expressive, multilingual speech for production voice agents, narration, and content | Premium – around 0.10 USD per 1K characters for Multilingual v2/v3 TTS, with monthly character bundles by plan |
Flash / Turbo (v2 / v2.5) | TTS / low‑latency | Character‑based (discounted credits, 0.5 credit per character for Flash/Turbo) | Real‑time or near‑real‑time speech where latency matters more than maximum fidelity | Mid‑tier – discounted vs Standard; Flash/Turbo typically billed at 0.05 USD per 1K characters in API pricing tables |
Specialized / advanced voices | TTS / voice cloning | Voice‑specific constraints (see plan limits on clones and usage) | High‑fidelity voice cloning, branded voices, and specialized audio experiences | Advanced tiers – priced via higher subscription plans (Creator, Pro, Scale) and API credit bundles |
Pricing tiers here are approximate and based on ElevenLabs’s public API pricing; Orq.ai may apply its own billing or BYOK mapping. Always check Orq.ai’s pricing page and your configured ElevenLabs provider for current per‑model rates, quotas, and billing details.
Why use ElevenLabs through Orq.ai?
Capability | Provider / models | Direct | Through Orq.ai |
|---|---|---|---|
Text‑to‑Speech | Multilingual v2/v3, Flash/Turbo TTS models | Call ElevenLabs directly via the ElevenAPI for text‑to‑speech, audio generation, and voice agents. | Use ElevenLabs TTS through Orq.ai’s router, combining voice generation with LLM routing, tracing, evals, budgets, and governance controls in one place. |
Voice cloning | Instant and Professional Voice Cloning | Use ElevenLabs Voice Cloning to create or manage custom voices, then call them via Eleven’s API | Centralize cloned‑voice usage in Orq.ai, tying specific voices to projects, routes, and cost controls alongside your LLM stack |
Conversational audio / agents | ElevenAgents, streaming TTS/S2T | Build voice agents and conversational audio flows using ElevenLabs’ own tooling and APIs | Integrate ElevenLabs audio into Orq.ai‑managed agents and workflows, so the same router that handles LLM calls also orchestrates speech in and out |
This gives teams a practical way to use ElevenLabs where it performs best while centralising routing, observability, evals, and cost controls across the wider model stack.
Pricing
Model rates
ElevenLabs model pricing may differ depending on whether you:
connect your own ElevenLabs API key and account (BYOK), or
use ElevenLabs models billed through Orq.ai where available
Pricing is primarily:
character‑based for text‑to‑speech, with different credit costs per character depending on model (Standard vs Flash/Turbo)
plan‑based for monthly character/credit bundles (Free, Starter, Creator, Pro, Scale)
Check the Orq.ai pricing page and your workspace’s provider configuration for current per‑model rates, quotas, and plan details.
Compatible frameworks and tools
Orq.ai exposes ElevenLabs via:
an HTTP / REST provider integration configured in the AI Router, and
an OpenAI‑compatible LLM layer for text, alongside separate audio routes for TTS where applicable.
That means:
LLM workflows built on Orq’s OpenAI‑compatible endpoint can call text models while delegating audio to ElevenLabs through Orq‑managed routes.
Agents, code assistants, and IDE tools that already integrate with Orq.ai (Cursor, VS Code, Claude Desktop, Warp, Zed, TRAE, etc.) can be extended to produce audio via ElevenLabs, depending on how you wire tools and routes.
Check the Orq.ai integration docs for the latest supported frameworks and tools for ElevenLabs.
FAQs
Do I need a separate ElevenLabs account to use ElevenLabs through Orq.ai?
You can either connect your own ElevenLabs API key into Orq.ai or, where available, use ElevenLabs usage billed via Orq.ai; the exact options depend on your Orq plan, region, and how ElevenLabs is configured in your workspace. In both cases, Orq.ai gives you one place to manage routing, observability, and cost controls around that ElevenLabs usage.
Can I route only some workflows to ElevenLabs and others to different providers?
Yes. You define routes per workflow in Orq.ai and decide which ones should use ElevenLabs vs other text or audio providers, so you can reserve ElevenLabs for specific languages, quality requirements, or voice workflows while sending other tasks elsewhere.
Does using ElevenLabs through Orq.ai add latency?
Orq.ai is designed as a lightweight router layer, so the added overhead is small compared to the audio generation time itself. You can use routing policies, caching (for reused prompts or responses), and provider selection to keep end‑to‑end performance within your targets.
Alternatives to
ElevenLabs
Anthropic
Use Claude Opus 4.7, Sonnet 4.6, Haiku 4.5, and other supported Claude models through one API.
Chat
Code
Reasoning
Vision
Models:
claude-opus-5
claude-sonnet-5
claude-fable-5
Open AI
Use OpenAI's foundation models through a single Orq.ai API. Route models such as GPT-4.1, GPT-4.1-mini, o3-mini, and GPT-4o-class models via Orq's AI Router for chat, reasoning, coding, and multimodal workloads.
Chat
Code
Image Generation
Reasoning
Speech
Vision
Models:
gpt-5.5 (EU)
gpt-5.6-luna (EU)
gpt-5.6-sol (EU)
Google AI
Use Google’s Gemini models through a single Orq.ai API. Route models such as Gemini 3.1 Pro, Gemini 2.5 Flash, and Gemini 2.0 Flash‑Lite via Orq’s AI Router for chat, reasoning, coding, and multimodal workloads.
Chat
Code
Embeddings
Image Generation
Reasoning
Speech
Vision
Models:
gemini-3.5-flash-lite (Gemini API)
gemini-3.6-flash (Gemini API)
Gemini 3 Pro Image
AWS
Use AWS Bedrock’s foundation models through a single Orq.ai API. Route models such as Amazon Nova, Amazon Titan Text, and compatible third‑party models exposed via Bedrock through Orq’s AI Router for chat, reasoning, coding, and multimodal workloads.
Chat
Code
Embeddings
Reasoning
Vision
Models:
eu.anthropic.claude-opus-5
global.anthropic.claude-opus-5
us.anthropic.claude-opus-5
