Google · Audio & Music

Hermes Agent x Gemini TTS

Gemini TTS belongs to the Google catalog on RunAPI and exposes Gemini 2.5 Pro TTS and Gemini 3.1 Flash TTS through one consistent API, SDK, and CLI surface.

2 variants from $1.40 / 1M tokens Commercial OK
Get API Key View Hermes Agent Docs

Prerequisite: npx runapi mcp install

Prompt

Prompt models

Use gemini-2.5-pro-tts when it matches the task: High-fidelity multi-speaker speech with expressive control for long-form dialogue.

You have access to RunAPI task tools for Gemini TTS.

Available Gemini TTS models:
- gemini-2.5-pro-tts: High-fidelity multi-speaker speech with expressive control for long-form dialogue
  endpoints: /api/v1/gemini_tts/text_to_speech
  request fields: model, temperature, scene, sample_context, speakers, dialogue_turns
- gemini-3.1-flash-tts: Fast multi-speaker speech for responsive dialogue and high-volume audio workflows
  endpoints: /api/v1/gemini_tts/text_to_speech
  request fields: model, temperature, scene, sample_context, speakers, dialogue_turns

Use the model ID and endpoint that match the user's request.
Example prompt: Generate a two-speaker podcast introduction with a calm British host and an energetic American guest.
/api/v1/gemini_tts/text_to_speech: Submit the task, poll for its status, then verify the completed output. POST /api/v1/gemini_tts/text_to_speech and save the returned Task id.
GET /api/v1/gemini_tts/text_to_speech/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.

Public Versions and Endpoints

Model ID Endpoints Price Catalog
gemini-2.5-pro-tts
/api/v1/gemini_tts/text_to_speech
$1.40 / 1M tokens Model detail
gemini-3.1-flash-tts
/api/v1/gemini_tts/text_to_speech
$1.40 / 1M tokens Model detail

Verify

Poll until the task reaches a terminal status

Select <model-id> to generate verification commands.

Configuration

Guide endpoint: <endpoint>

Select <model-id> to generate a request with the endpoint's public input contract.
How it works

Get Started in 3 Steps

  1. Choose a model ID

    Select a public catalog model ID and review its endpoint and current starting price.

  2. Configure RunAPI

    Set RUNAPI_API_KEY before making the endpoint request.

  3. Verify the result

    For asynchronous endpoints, poll the same endpoint until the Task reaches a terminal status.

What to Build with Hermes Agent + Gemini TTS

  • Voiceover and narration

    Turn scripts into spoken audio for videos, courses, and product demos with models that generate speech.

  • Music and soundtracks

    Create background tracks and jingles from a description of genre, mood, and tempo with models that generate music.

  • Transcription and audio processing

    Transcribe recordings or clean up and transform existing audio with models that accept audio input.

Why Use Gemini TTS Through RunAPI + Hermes Agent

  • 2 variants, one API key

    Use one RunAPI connection to choose among the live model variants without changing your integration.

  • Clear usage pricing

    See current catalog pricing before you send a request, with no subscription or minimum spend required.

  • Automatic task workflows

    Submit, poll, and collect asynchronous results through a consistent task workflow without writing manual polling code.

Hermes Agent + Gemini TTS Questions

Which Gemini TTS models are available?

RunAPI supports Gemini 2.5 Pro TTS and Gemini 3.1 Flash TTS through the same text-to-speech endpoint and request shape.

How do I configure multiple speakers?

Add a speaker configuration for each participant using a unique Speaker N identifier, then assign each dialogue turn to one of those identifiers.

What can I control for each speaker?

Each speaker has a voice, accent, delivery style, and pace, with an optional audio profile for additional voice direction.

How do scene and sample context affect the request?

Scene describes the recording environment, while sample context sets the overall tone and delivery guidance for the dialogue.

How are completed audio results returned?

Query the task or receive its callback after completion; the response contains an audios list with the generated file URL.

Which model ID should I use?

Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.

Does this guide configure a chat model?

No. This Model Line uses the endpoint workflow shown here and is not presented as an agent chat model.

Start using Gemini TTS with Hermes Agent

Get API Key Read Quickstart

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.

Contact Us