Gemini 2.5 Pro Preview TTS
google / gemini-2-5-pro-tts

Gemini 2.5 Pro Preview TTS is Google’s premium text-to-speech model designed for studio-quality, high-fidelity audio generation. It enables developers to create realistic AI voices with natural language instructions, expressive speech, and long-form audio capabilities.

Pricing: Input 140 credits / 1M tokens (≈ $0.70), Audio Output 2,800 credits / 1M tokens (≈ $14.00). ~30% cheaper than official pricing. High-tier top-ups (+10% bonus) bring effective pricing down to ~90% of the above.
Input
0 / 2
No items yet. Click Add to start.

At least 1 item(s) required

0
No items yet. Click Add to start.

At least 1 item(s) required

Controls the randomness of the speech output. Higher values produce more creative and varied delivery, while lower values make the output more predictable and focused. Default value: 1

scene description

0/1000

Example Context / Overall Tone

0/1000
Output
output typeaudio

README

Complete guide to using google/gemini-2-5-pro-tts

Gemini 2.5 Pro Preview TTS API for Advanced AI Voice Generation

Original image
Studio-Quality AI Voice Generation with Gemini 2.5 Pro Preview TTS API
Expressive Voice and Style Control with Gemini 2.5 Pro Text-to-Speech API
Natural Multi-Speaker Dialogue Generation with Google Gemini 2.5 Pro TTS
Long-Form Audio Creation with Gemini 2.5 Pro Preview TTS API
FeatureGemini 2.5 Pro TTS APIGemini 2.5 Flash TTS API
Primary FocusPremium AI voice quality with advanced expression, natural speech, and professional audio generationFast and efficient AI voice generation optimized for low-latency applications
Best ForAudiobooks, podcasts, video narration, creative content, and long-form audio workflowsReal-time voice assistants, customer support agents, and high-volume voice applications
Voice QualityDelivers studio-quality speech with realistic pronunciation, natural prosody, emotional expression, and human-like deliveryProvides high-quality AI voices with faster generation speed for interactive experiences
Style & Emotion ControlOffers stronger style prompt following with detailed control over emotion, tone, pacing, and speaking styleSupports voice customization while focusing on speed and efficient generation
Multi-Speaker SupportDesigned for natural multi-speaker dialogue with consistent character voices and complex conversationsSupports conversational voice generation for interactive applications and voice agents
LatencyPrioritizes maximum audio quality and expressive performance over response speedOptimized for faster response times and real-time voice interactions
Long-Form ContentBetter suited for audiobooks, courses, documentaries, and extended narration projectsBetter suited for short-form content and applications requiring quick audio responses
Recommended Use CasesProfessional voice applications requiring premium quality, emotional depth, and natural storytellingAI assistants, scalable SaaS products, and applications where speed is the top priority

Gemini 2.5 Pro Preview TTS API is Google’s advanced text-to-speech API designed for high-quality AI voice generation. It converts text into natural speech with expressive styles, emotional control, and realistic voice performance for developers and SaaS applications.

Developers can use Gemini 2.5 Pro TTS API through Kie.ai by creating an account, getting an API key, testing voice generation in the playground, and integrating the API into their applications with simple API requests.

Send POST https://api.kie.ai/api/v1/jobs/createTask with model set to google/gemini-2-5-pro-tts. The input needs speakers (each with a speaker_id in the "Speaker N" format, a voice_name and an accent) and dialogue_turns (each with a speaker_id and the text to speak); scene, sample_context, temperature and each speaker's style and pace are optional. The request returns a taskId: add a callBackUrl to be notified when the audio is ready, or poll GET /api/v1/jobs/recordInfo?taskId=…. Errors come back with HTTP status 200 and an error code in the body (401 invalid or missing API key, 402 insufficient credits, 429 rate limit exceeded), so always check code. All parameters are in the Gemini 2.5 Pro TTS API docs.

Kie.ai provides Gemini 2.5 Pro TTS free credits for new users to test AI voice generation capabilities. After testing, developers can choose a suitable pricing plan based on their audio generation requirements and usage volume.

On Kie.ai, input text costs 140 credits per 1M tokens (about $0.70) and audio output costs 2,800 credits per 1M tokens (about $14.00). Google's standard (non-batch) Gemini API rate for gemini-2.5-pro-preview-tts is $1.00 per 1M input tokens and $20.00 per 1M audio output tokens as of November 2026, so Kie.ai is about 30% lower. Prices may be updated; the pricing card at the top of this page always shows the current rate.

Gemini 2.5 Pro TTS focuses on premium voice quality, emotional expression, and long-form audio generation, while Gemini 2.5 Flash TTS is optimized for faster responses and real-time voice applications.

Yes. Gemini 2.5 Pro TTS API supports multi-speaker dialogue generation, allowing developers to create conversations with different voices for AI podcasts, virtual characters, interactive stories, and voice applications.

Each request supports up to 2 speakers, and each speaker uses one of 30 prebuilt voices (Achernar, Achird, Algenib, Algieba, Alnilam, Aoede, Autonoe, Callirrhoe, Charon, Despina, Enceladus, Erinome, Fenrir, Gacrux, Iapetus, Kore, Laomedeia, Leda, Orus, Puck, Pulcherrima, Rasalgethi, Sadachbia, Sadaltager, Schedar, Sulafat, Umbriel, Vindemiatrix, Zephyr, Zubenelgenubi). You can set an accent (Neutral, American, British, Transatlantic or Australian), a style (Vocal Smile, Newscaster, Whisper, Empathetic, Promo/Hype or Deadpan) and a pace (Natural, Rapid Fire, The Drift or Staccato), plus a scene, an overall tone and a temperature from 0 to 2. Each dialogue turn takes up to 10,000 characters with inline tone tags, and the output is WAV (16-bit PCM, 24 kHz, mono).

Yes. Gemini 2.5 Pro Text-to-Speech API is designed for long-form audio generation, making it suitable for audiobooks, educational courses, documentation narration, and other extended voice workflows.

Create an account on Kie.ai, open the API Keys page (kie.ai/api-key) and generate a key. Send it with every request as the header Authorization: Bearer YOUR_API_KEY. The same key and credit balance work for every model on Kie.ai, and you can limit each key with hourly, daily and total usage caps and an IP whitelist.

Yes. Kie.ai provides an online playground where developers can test Gemini 2.5 Pro TTS online, experiment with voice prompts, adjust styles, and evaluate generated audio before building their products.