2 models · speech
Gemini TTS API
Gemini TTS is a family of AI speech models made by Google. varg runs 2 of them on one API key: Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. Between them they cover text to speech; they return audio.
- Price
- From $0.01 per run Gemini 3.8 Flash TTS
- Made by
- Flagship id
gemini_3_8_flash_tts
Every Gemini TTS 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": "gemini_3_8_flash_tts",
"voice": "Kore"
}'Gemini TTS models and prices
Gemini TTS on varg starts from $0.01 per run (Gemini 3.8 Flash TTS). 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 |
|---|---|---|---|---|
Gemini 3.8 Flash TTSgemini_ | Gemini 3.8 Flash TTS by Google. Natural speech in 130 languages with 30 voices, style instructions and two-speaker dialogue. | Text to speech | From $0.01 per run$0.045/1k chars | ~8 s |
Gemini 3.8 Flash-Lite TTSgemini_ | Gemini 3.8 Flash-Lite TTS by Google. Low-cost natural speech in 101 languages with 30 voices and two-speaker dialogue. | Text to speech | From $0.01 per run$0.03/1k chars | ~6 s |
Call the Gemini TTS API
The call below runs Gemini 3.8 Flash TTS. For another Gemini TTS 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": "gemini_3_8_flash_tts",
"voice": "Kore"
}'From Claude, ChatGPT or Cursor (MCP)
The varg MCP server, https://mcp.varg.ai/mcp, runs Gemini 3.8 Flash TTS 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": "gemini_3_8_flash_tts",
"voice": "Kore"
},
"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":"gemini_3_8_flash_tts","voice":"Kore"}'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
How to use Gemini TTS
Step-by-step pages on varg how to.
Gemini TTS API: questions
- How much does the Gemini TTS API cost on varg?
- The lowest price the catalog states in the Gemini TTS family is from $0.01 per run, on Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. 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 Gemini TTS models are on varg?
- 2: Gemini 3.8 Flash TTS (from $0.01 per run) and Gemini 3.8 Flash-Lite TTS (from $0.01 per run). Each has its own page with the parameters and a call to copy.
- How long do Gemini TTS requests take?
- Typically from about 6 s (Gemini 3.8 Flash-Lite TTS) to about 8 s (Gemini 3.8 Flash TTS), 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 Gemini TTS 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": "gemini_3_8_flash_tts". 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 Gemini TTS 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": "gemini_3_8_flash_tts".
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/gemini_3_8_flash_tts.md (swap the id), and every model is listed in varg.ai/models/llms.txt.