Flexible parameters
Configure 5 documented parameters, including dialogue_turns, sample_context, scene, speakers, temperature.
High-fidelity multi-speaker speech with expressive control for long-form dialogue
curl -X POST https://runapi.ai/api/v1/gemini_tts/text_to_speech \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-2.5-pro-tts",
"text": "Generate a two-speaker podcast introduction with a calm British host and an energetic American guest."
}'
import { GeminiTtsClient } from "@runapi.ai/gemini-tts";
const client = new GeminiTtsClient();
const result = await client.textToSpeech.run({
model: "gemini-2.5-pro-tts",
text: "Generate a two-speaker podcast introduction with a calm British host and an energetic American guest.",
});
import os
import requests
response = requests.post(
"https://runapi.ai/api/v1/gemini_tts/text_to_speech",
headers={"Authorization": f"Bearer {os.environ['RUNAPI_API_KEY']}"},
json={"model":"gemini-2.5-pro-tts","text":"Generate a two-speaker podcast introduction with a calm British host and an energetic American guest."}
)
response.raise_for_status()
<?php
$client = curl_init("https://runapi.ai/api/v1/gemini_tts/text_to_speech");
curl_setopt_array($client, [
CURLOPT_HTTPHEADER => ["Authorization: Bearer " . getenv("RUNAPI_API_KEY"), "Content-Type: application/json"],
CURLOPT_POSTFIELDS => json_encode([
'model' => 'gemini-2.5-pro-tts',
'text' => 'Generate a two-speaker podcast introduction with a calm British host and an energetic American guest.',
])
]);
$response = curl_exec($client);
RunApi client = new RunApi(System.getenv("RUNAPI_API_KEY"));
Task task = client.textToSpeech().run({"model":"gemini-2.5-pro-tts","text":"Generate a two-speaker podcast introduction with a calm British host and an energetic American guest."});
task.waitForResult();
require "runapi/gemini_tts"
client = RunApi::GeminiTts::Client.new
result = client.text_to_speech.run(
model: "gemini-2.5-pro-tts",
text: "Generate a two-speaker podcast introduction with a calm British host and an energetic American guest."
)
client := runapi.NewClient(os.Getenv("RUNAPI_API_KEY"))
task, err := client.textToSpeech.Run({"model":"gemini-2.5-pro-tts","text":"Generate a two-speaker podcast introduction with a calm British host and an energetic American guest."})
if err != nil { log.Fatal(err) }
task.Wait()
$ runapi generate \
--model gemini-2.5-pro-tts \
--endpoint text_to_speech \
--wait
2 versions available
Pick any model and generate in seconds.
No models are available right now.
| Provider | |
| Model ID | gemini-2.5-pro-tts |
| Modality | Audio & Music |
| Task types | Asynchronous |
| API endpoint | /api/v1/gemini_tts/text_to_speech |
| Billing unit | 1K tokens |
| Input parameters | callback_url, dialogue_turns, model, sample_context, scene, speakers, temperature |
| Catalog status | Operational |
Sign up for free and create an API key for gemini-2.5-pro-tts from the dashboard.
POST to /api/v1/gemini_tts/text_to_speech with the gemini-2.5-pro-tts model slug and your parameters.
Poll the task or follow the callback to retrieve the completed gemini-2.5-pro-tts result.
Configure 5 documented parameters, including dialogue_turns, sample_context, scene, speakers, temperature.
Exposes 1 public endpoint(s): text_to_speech.
Asynchronous tasks accept a callback URL for completion notifications.
Metered by 1K tokens with no subscription requirement.
sceneScene and recording environment.
speakersNon-empty speaker configurations with unique Speaker N identifiers.
temperatureSampling temperature.
callback_urlWebhook URL for async notifications.
dialogue_turnsNon-empty ordered dialogue turns whose speaker ids reference configured speakers.
sample_contextOverall delivery context and tone.
Generate royalty-free background music matched to episode mood without licensing fees.
Generate adaptive ambient soundscapes and effects for procedurally generated levels.
Generate custom voiceovers and sound effects for client spots without a recording studio.
Pass the model ID shown in the quickstart.
Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades.
Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape.
Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery.
Open an issue on the public GitHub repo or email support at [email protected]. Include the task ID and model ID so the team can investigate the specific generation.
No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider.
We're here to help with enterprise setup, integrations, and technical questions.
Contact Us