# The New Gemini Text to Speech Source: https://www.youtube.com/watch?v=lfxfVQ0QzOk Recap page: https://rapidrecap.app/video/lfxfVQ0QzOk Generated: 2025-12-19T14:03:37.608+00:00 --- ## Quick Overview Google AI Studio has released significant enhancements to its Gemini 2.5 Flash and Gemini 2.5 Pro Text-to-Speech (TTS) preview models, introducing improved expressivity, precision pacing, and seamless dialogue capabilities, with the Flash model offering faster generation than the Pro version. **Key Points:** - The key improvements in Gemini 2.5 TTS models include enhanced expressivity (richer tone versatility), precision pacing (smarter context-aware speed adjustments), and seamless dialogue (consistent character voices). - The Gemini 2.5 Flash TTS preview model is optimized for performance and low latency, while the Gemini 2.5 Pro TTS preview model is optimized for higher quality outputs. - The Gemini TTS models can automatically detect input language and support 24 languages, including European and Asian languages. - Users can control style, tone, accent, and pace using natural language prompts, demonstrated by generating a spooky whisper and a fast-paced podcast debate. - Multi-speaker audio generation is supported by specifying different `SpeakerVoiceConfig` objects for each speaker, allowing assignment of distinct voices like 'Puck' (enthusiastic) and 'Fenrir' (skeptical). - The paid tier pricing for Gemini 2.5 Flash TTS is $0.50 per 1M text tokens (input) and $10.00 per 1M audio tokens (output), while the Pro version is $1.00 (text) and $20.00 (audio) for batch processing. - The TTS models have a context window limit of 32k tokens, which is smaller than the 1 million token context window of the base Gemini models. ![Screenshot at 00:03: The video opens by showing a social media post announcing significant enhancements to the Gemini 2.5 Flash and Gemini 2.5 Pro Text-to-Speech \(TTS\) preview models, listing key improvements like enhanced expressivity and precision pacing.](https://ss.rapidrecap.app/screens/lfxfVQ0QzOk/00-00-03.png) **Context:** This video details the significant enhancements made to Google's Gemini 2.5 Text-to-Speech (TTS) preview models, specifically Gemini 2.5 Flash and Gemini 2.5 Pro. The presenter walks through a Google Colab notebook demonstrating how to use the updated API to generate more expressive, context-aware, and multi-speaker audio content, highlighting new prompting capabilities and pricing structures. ## Detailed Analysis The video showcases the new features of the Gemini 2.5 Text-to-Speech (TTS) preview models, which are built upon the larger Gemini language model. Key improvements focus on better control over audio output: Enhanced expressivity allows for richer tone versatility and stricter adherence to style prompts; Precision pacing enables smarter, context-aware speed adjustments; and Seamless dialogue ensures consistent character voices in multi-speaker scenarios. The presenter demonstrates these capabilities using Python code in a Google Colab notebook. First, a basic audio generation is shown, requiring the configuration parameter `response_modalities: ['Audio']` to request audio output. The models support 24 languages, automatically detecting the input language using BCP-47 codes. Advanced prompting allows users to dictate style, tone, accent, and pace, as demonstrated with a 'spooky whisper' and a fast-paced comedy show script with contrasting speaker personalities (enthusiastic vs. skeptical). The multi-speaker feature requires configuring `MultiSpeakerVoiceConfig` with specific `SpeakerVoiceConfig` objects, assigning prebuilt voices like 'Puck' and 'Fenrir' to different speakers. The presenter notes that the Flash model (optimized for performance) is faster in experiments than the Pro model (optimized for quality). Finally, pricing tiers are reviewed: Gemini 2.5 Flash standard tier charges $0.50/1M text tokens and $10.00/1M audio tokens in the paid tier, while the Pro version is $1.00/1M text and $20.00/1M audio (batch pricing). A limitation noted is that TTS sessions have a smaller context window limit of 32k tokens compared to the 1 million tokens supported by the base Gemini models. ### Gemini 2.5 TTS Model Enhancements - Enhanced expressivity for richer tone versatility - Precision pacing for smarter context-aware speed adjustments - Seamless dialogue for consistent multi-speaker voices ### Model Variants and Optimization - Gemini 2.5 Flash optimized for performance/low latency - Gemini 2.5 Pro optimized for quality ### Language Support - Automatic input language detection across 24 supported languages, including European and Asian languages. ### Advanced Prompting Control - Control over style, tone, accent, and pace using natural language prompts (e.g., 'spooky whisper', 'energetic pace'). ### Multi-Speaker Configuration - Use `MultiSpeakerVoiceConfig` to assign specific prebuilt voices (e.g., 'Puck' for enthusiastic, 'Fenrir' for skeptical) to different speakers. ### Pricing Comparison (Per 1M Tokens, Standard Tier) - Flash Audio Output is $10.00; Pro Audio Output is $20.00. ### Limitations - TTS models have a context window limit of 32k tokens, unlike the 1M token context of base Gemini models. ![Screenshot at 00:03: Announcement graphic displaying 'Gemini 2.5 Text-to-Speech' and highlighting key improvements like expressivity and pacing.](https://ss.rapidrecap.app/screens/lfxfVQ0QzOk/00-00-03.png) ![Screenshot at 00:14: Code snippet demonstrating the multi-speaker configuration using SpeakerVoiceConfig to assign 'Puck' \(Enthusiastic\) and 'Fenrir' \(Skeptical\) voices.](https://ss.rapidrecap.app/screens/lfxfVQ0QzOk/00-00-14.png) ![Screenshot at 01:31: The video transitions to showing the Google AI Studio interface, demonstrating a prompt for generating French audio output.](https://ss.rapidrecap.app/screens/lfxfVQ0QzOk/00-01-31.png) ![Screenshot at 03:50: Code block showing the basic structure for generating audio output by setting response\_modalities: \['Audio'\] in the configuration.](https://ss.rapidrecap.app/screens/lfxfVQ0QzOk/00-03-50.png) ![Screenshot at 10:11: Table detailing the 30 available prebuilt voice options for the TTS models, listing names like Zephyr, Puck, and Kore.](https://ss.rapidrecap.app/screens/lfxfVQ0QzOk/00-10-11.png)