gemini-2.5-flash-preview-tts API

What is gemini-2.5-flash-preview-tts?

Use the public identifier gapgpt-gemini-25-flash-preview-tts-4a31ca2be6 for gemini-2.5-flash-preview-tts in ServerNet. The gateway uses this identifier to select the configured route; the developer is Google.

For gemini-2.5-flash-preview-tts, validate the request against the gateway’s text input contract. Features of a native Gemini API may require a different integration.

Where to use gemini-2.5-flash-preview-tts

• Check whether gemini-2.5-flash-preview-tts synthesizes speech or transcribes audio.
• Evaluate pronunciation or transcription quality with a representative sample.
• Check audio duration, output format and supported voices or languages for your application.

Build your integration

Audio execution needs explicit text or file limits and a verified native endpoint. Use the documented route once it becomes available; a text chat request does not perform an audio task.

Inputs and service limits

Character, duration and generation limits differ between audio models. Voice conditioning and uploaded audio can add consumption. Supported languages and voices must come from the model’s confirmed contract.

Image, audio, video and other native services can use different billing units. A token tariff is not a valid substitute. Sale opens only after the execution path and bounded billing contract are verified.

Accepted ServerNet API parameters

Gateway request contract: 2026-10-11. These fields and defaults are enforced by /v1/inference; availability is shown above. Text byte limits are measured as UTF-8 bytes.

Connect to gemini-2.5-flash-preview-tts API

Enable ai:native on your key and ai:models:read to check availability. Set SERVERNET_API_KEY in your server environment. Change the idempotency key for each new request; keep it unchanged only for an identical retry.

This example documents the request format. Send it only after this model appears in GET /v1/models.

curl https://servernet.cloud/v1/inference \
  -H "Authorization: Bearer $SERVERNET_API_KEY" \
  -H 'Content-Type: application/json' \
  -H 'Idempotency-Key: CHANGE_FOR_EACH_NEW_REQUEST' \
  -d '{
    "model": "gapgpt-gemini-25-flash-preview-tts-4a31ca2be6",
    "voice": "Kore",
    "max_output_tokens": 2048,
    "input": "Hello from ServerNet"
}'

Use the same Idempotency-Key when retrying an identical request. Successful responses are replayed without a second charge for 24 hours. Do not automatically retry when x-should-retry:false is present. The key is shown once. Store it in a server environment variable. Keep it out of browser code, GitHub and logs.

Compare models for the same task