14 models · speech and music
ElevenLabs API
ElevenLabs is a family of AI speech and music models. varg runs 14 of them on one API key: ElevenLabs v4, ElevenLabs Music v2.5, ElevenLabs v4 Turbo and 11 more. Between them they cover text to speech, music and text to audio; they return audio.
- ElevenLabs v4
- From $0.01 per run
- Flagship id
eleven_v4
Every ElevenLabs model runs on one varg API key and one credit balance, the same as every other model here. You pay the provider's price, with no markup.
curl -X POST https://api.varg.ai/v2/tools/speech/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "eleven_v4",
"text": "[excited] We just shipped it! [laughs] Okay, okay — let me walk you through what changed.",
"voice": "rachel"
}'ElevenLabs models and prices
Prices are in US dollars and are the provider's own, with no markup. A "from" price is the cheapest request the catalog states for that model; each model's page has every rate and input. The descriptions are the catalog's own, shortened.
| Model | Catalog description | Takes | Price | Typical time |
|---|---|---|---|---|
ElevenLabs v4eleven_ | ElevenLabs v4. The most natural, expressive speech: top of the TTS arena, 90+ languages, audio tags and voice clones. | Text to speech | From $0.01 per run$0.08/1k chars | ~4 s |
ElevenLabs Music v2.5eleven_ | ElevenLabs Music v2.5. Studio-grade songs with vocals or instrumentals, 3 seconds to 10 minutes. | Music | From $0.01 per run$0.0025/s | ~45 s |
ElevenLabs v4 Turboeleven_ | ElevenLabs v4 Turbo. Real-time (~100 ms) expressive speech at half the price of v4; #1 on the TTS arena. | Text to speech | From $0.01 per run$0.04/1k chars | ~2 s |
ElevenLabs v3eleven_ | — | Text to speech | From $0.01 per run$0.10/1k chars | ~3 s |
ElevenLabs Flash v2.5eleven_ | Flash variant. | Text to speech | From $0.01 per run$0.05/1k chars | ~3 s |
ElevenLabs Flash v2eleven_ | Previous-gen flash model. Good baseline TTS. | Text to speech | From $0.01 per run$0.05/1k chars | ~3 s |
ElevenLabs Multilingual v2eleven_ | Multilingual support. 29 languages with natural prosody. | Text to speech | From $0.01 per run$0.10/1k chars | ~3 s |
Eleven Turboeleven_ | Alias of ElevenLabs Turbo v2. Text to speech, billed per character. | Text to speech | From $0.01 per run$0.05/1k chars | ~3 s |
ElevenLabs Turbo v2.5eleven_ | Turbo speed. Low latency, good for real-time applications. | Text to speech | From $0.01 per run$0.05/1k chars | ~3 s |
ElevenLabs Turbo v2eleven_ | Previous-gen turbo model. Stable and reliable. | Text to speech | From $0.01 per run$0.05/1k chars | ~3 s |
Turboturbo | Alias of ElevenLabs Turbo v2. Text to speech, billed per character. | Text to speech | From $0.01 per run$0.05/1k chars | ~3 s |
Eleven Musiceleven_ | ElevenLabs Music. A music track from a text prompt, from 1 second to 10 minutes. | Music | From $0.01 per run$0.0025/s | ~30 s |
ElevenLabs Sound Effects v3eleven_ | ElevenLabs SFX v3. Sound effects from a text prompt (up to 450 characters), 0.5-30 s or a length the model picks, with optional seamless looping. | Text to audio | $0.002/s | ~15 s |
ElevenLabs Musicmusic_ | AI music generation. Prompt-driven background tracks. | Music | From $0.01 per run$0.0025/s | ~30 s |
Call the ElevenLabs API
The call below runs ElevenLabs v4. For another ElevenLabs model, put its id from the table in "model"; the rest of the request keeps its shape.
REST
POST https://api.varg.ai/v2/tools/speech/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away; poll GET /v2/jobs/{id} until its status is completed, then read output.outputs[0].url.
curl -X POST https://api.varg.ai/v2/tools/speech/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "eleven_v4",
"text": "[excited] We just shipped it! [laughs] Okay, okay — let me walk you through what changed.",
"voice": "rachel"
}'From Claude, ChatGPT or Cursor (MCP)
The varg MCP server, https://mcp.varg.ai/mcp, runs ElevenLabs v4 with call_tool. Sign in with varg, no API key to paste. How to connect it
claude mcp add --transport http varg https://mcp.varg.ai/mcp{
"tool": "speech",
"input": {
"model": "eleven_v4",
"text": "[excited] We just shipped it! [laughs] Okay, okay — let me walk you through what changed.",
"voice": "rachel"
},
"wait": true
}From a terminal (CLI)
vargai is the varg command line: every tool of the MCP server is a command. Install and log in
curl -fsSL https://varg.ai/install | sh
vargai call_tool --tool speech '{"model":"eleven_v4","text":"[excited] We just shipped it! [laughs] Okay, okay — let me walk you through what changed.","voice":"rachel"}'How billing works
Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. varg's fee is on the top-up, not on the run: 5.5% of the credits you buy ($0.80 at the least), or 8% for a team workspace. Pricing
ElevenLabs compared
Price, limits and inputs side by side, from the same catalog as this page.
How to use ElevenLabs
Step-by-step pages on varg how to.
ElevenLabs API: questions
- How much does the ElevenLabs API cost on varg?
- Among the ElevenLabs models with a stated run price, the lowest is from $0.01 per run, on ElevenLabs v4, ElevenLabs Music v2.5, ElevenLabs v4 Turbo, ElevenLabs v3, ElevenLabs Flash v2.5, ElevenLabs Flash v2, ElevenLabs Multilingual v2, Eleven Turbo, ElevenLabs Turbo v2.5, ElevenLabs Turbo v2, Turbo, Eleven Music and ElevenLabs Music. ElevenLabs Sound Effects v3 ($0.002/s) is billed by rate with no stated minimum, so a short request can cost less. Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.
- Which ElevenLabs models are on varg?
- 14: ElevenLabs v4 (from $0.01 per run), ElevenLabs Music v2.5 (from $0.01 per run), ElevenLabs v4 Turbo (from $0.01 per run), ElevenLabs v3 (from $0.01 per run), ElevenLabs Flash v2.5 (from $0.01 per run), ElevenLabs Flash v2 (from $0.01 per run), ElevenLabs Multilingual v2 (from $0.01 per run), Eleven Turbo (from $0.01 per run), ElevenLabs Turbo v2.5 (from $0.01 per run), ElevenLabs Turbo v2 (from $0.01 per run), Turbo (from $0.01 per run), Eleven Music (from $0.01 per run), ElevenLabs Sound Effects v3 ($0.002/s) and ElevenLabs Music (from $0.01 per run). Each has its own page with the parameters and a call to copy.
- How long do ElevenLabs requests take?
- Typically from about 2 s (ElevenLabs v4 Turbo) to about 45 s (ElevenLabs Music v2.5), by the catalog's estimates for each model's fastest route. The API answers at once with a job id, so nothing waits on an open connection while it runs.
- How do I call the ElevenLabs API?
- Send POST https://api.varg.ai/v2/tools/speech/call with the header "Authorization: Bearer $VARG_API_KEY" and a JSON body that includes "model", for example "model": "eleven_v4". The call answers 202 with a job right away. Poll GET https://api.varg.ai/v2/jobs/{id} until "status" is "completed", then read output.outputs[0].url, or pass options.webhook_url to be called back.
- Can I use ElevenLabs from Claude, ChatGPT or Cursor?
- Yes. Add the varg MCP server (https://mcp.varg.ai/mcp) to Claude, ChatGPT, Cursor or any other MCP client and sign in with varg, with no API key to paste. The agent runs a model with call_tool, passing tool "speech" and the model id, for example "model": "eleven_v4".
More model APIs
Same API key, same request shape: change the model string to switch.
For AI agents: each model above has its full spec as Markdown at varg.ai/models/eleven_v4.md (swap the id), and every model is listed in varg.ai/models/llms.txt.