diff --git a/fern/assets/scripts/stt-calculator.js b/fern/assets/scripts/stt-calculator.js new file mode 100644 index 000000000..963576ffc --- /dev/null +++ b/fern/assets/scripts/stt-calculator.js @@ -0,0 +1,40 @@ +const pricingData = { + free: { basePrice: 0, includedHours: 2.5, extraHourCost: null }, + starter: { basePrice: 5, includedHours: 12.5, extraHourCost: 0.4 }, + creator: { basePrice: 22, includedHours: 63, extraHourCost: 0.35 }, + pro: { basePrice: 99, includedHours: 320, extraHourCost: 0.31 }, + scale: { basePrice: 330, includedHours: 1220, extraHourCost: 0.27 }, + business: { basePrice: 1320, includedHours: 6000, extraHourCost: 0.22 }, +}; + +function formatPrice(value) { + return '$' + value.toFixed(2).replace(/\\B(?=(\\d{3})+(?!\\d))/g, ','); +} + +function calculatePrice() { + const tier = document.getElementById('tier-select').value; + const hours = parseFloat(document.getElementById('hours-input').value) || 0; + const tierData = pricingData[tier]; + + const basePrice = tierData.basePrice; + const extraHours = Math.max(0, hours - tierData.includedHours); + const extraHoursCost = tierData.extraHourCost ? extraHours * tierData.extraHourCost : 0; + const totalCost = basePrice + extraHoursCost; + + document.getElementById('base-price').textContent = formatPrice(basePrice); + document.getElementById('extra-hours-cost').textContent = formatPrice(extraHoursCost); + document.getElementById('total-cost').textContent = formatPrice(totalCost); + + // Add animation class to prices + document.querySelectorAll('.price').forEach((el) => { + el.classList.add('price-updated'); + setTimeout(() => el.classList.remove('price-updated'), 300); + }); +} + +// Initialize calculator +document.getElementById('tier-select')?.addEventListener('change', calculatePrice); +document.getElementById('hours-input')?.addEventListener('input', calculatePrice); + +// Calculate initial values +calculatePrice(); diff --git a/fern/docs.yml b/fern/docs.yml index 5f4567f92..fe936536c 100644 --- a/fern/docs.yml +++ b/fern/docs.yml @@ -765,6 +765,8 @@ js: strategy: lazyOnload - url: https://elevenlabs.io/player/audioNativeHelper.js strategy: lazyOnload + - path: assets/scripts/stt-calculator.js + strategy: lazyOnload analytics: posthog: diff --git a/fern/docs/pages/capabilities/speech-to-text.mdx b/fern/docs/pages/capabilities/speech-to-text.mdx index 73de769f0..ca9af7a91 100644 --- a/fern/docs/pages/capabilities/speech-to-text.mdx +++ b/fern/docs/pages/capabilities/speech-to-text.mdx @@ -424,6 +424,169 @@ The output is classified in three category types: - `spacing` - The space between words, not applicable for languages that don't use spaces like Japanese, Mandarin, Thai, Lao, Burmese and Cantonese. - `audio_event` - Non-speech sounds like laughter or applause. Also includes verbatim noises like "um" or "ah". +## Pricing + +| Tier | Price | Hours included | Cost per extra hour | +| -------- | ------- | -------------- | ------------------- | +| Free | \$0 | 2.5 | Unavailable | +| Starter | \$5 | 12.5 | \$0.40 | +| Creator | \$22 | 63 | \$0.35 | +| Pro | \$99 | 320 | \$0.31 | +| Scale | \$330 | 1220 | \$0.27 | +| Business | \$1,320 | 6000 | \$0.22 | + +### Price Calculator + +
+
+
+ + +
+ +
+ + +
+
+ +
+
+ Monthly subscription + $0.00 +
+
+ Additional hours cost + $0.00 +
+
+ Total monthly cost + $0.00 +
+
+
+ + + ## Supported variants Scribe v1 is available in two variants: diff --git a/fern/docs/pages/capabilities/text-to-speech.mdx b/fern/docs/pages/capabilities/text-to-speech.mdx index bac9e6a4e..0ebdd7b2a 100644 --- a/fern/docs/pages/capabilities/text-to-speech.mdx +++ b/fern/docs/pages/capabilities/text-to-speech.mdx @@ -37,7 +37,7 @@ Explore our [voice library](https://elevenlabs.io/community) to find the perfect For real-time applications, Flash v2.5 provides ultra-low 75ms latency, while Multilingual v2 delivers the highest quality audio with more nuanced expression. - +
[Explore all](/docs/models)
diff --git a/fern/docs/pages/models.mdx b/fern/docs/pages/models.mdx index d12952541..0f63752d8 100644 --- a/fern/docs/pages/models.mdx +++ b/fern/docs/pages/models.mdx @@ -120,6 +120,21 @@ With its lower price point and 75ms latency, Flash v2.5 is the cost-effective op +## Character limits + +The maximum number of characters supported in a single text-to-speech request varies by model. + +| Model ID | Character limit | Approximate audio duration | +| ------------------------ | --------------- | -------------------------- | +| `eleven_flash_v2_5` | 40,000 | ~40 minutes | +| `eleven_flash_v2` | 30,000 | ~30 minutes | +| `eleven_multilingual_v2` | 10,000 | ~10 minutes | +| `eleven_multilingual_v1` | 10,000 | ~10 minutes | +| `eleven_english_sts_v2` | 10,000 | ~10 minutes | +| `eleven_english_sts_v1` | 10,000 | ~10 minutes | + +For longer content, consider splitting the input into multiple requests. + ## Scribe v1 Scribe v1 is our state-of-the-art speech recognition model designed for accurate transcription across 99 languages. It provides precise word-level timestamps and advanced features like speaker diarization and dynamic audio tagging. @@ -140,21 +155,6 @@ Key features: Read more about Scribe v1 [here](/docs/capabilities/speech-to-text). -## Character limits - -The maximum number of characters supported in a single text-to-speech request varies by model. - -| Model ID | Character limit | Approximate audio duration | -| ------------------------ | --------------- | -------------------------- | -| `eleven_flash_v2_5` | 40,000 | ~40 minutes | -| `eleven_flash_v2` | 30,000 | ~30 minutes | -| `eleven_multilingual_v2` | 10,000 | ~10 minutes | -| `eleven_multilingual_v1` | 10,000 | ~10 minutes | -| `eleven_english_sts_v2` | 10,000 | ~10 minutes | -| `eleven_english_sts_v1` | 10,000 | ~10 minutes | - -For longer content, consider splitting the input into multiple requests. - ## Concurrency and priority Your subscription plan determines how many requests can be processed simultaneously and the priority level of your requests in the queue. diff --git a/fern/docs/pages/product-guides/playground/text-to-speech.mdx b/fern/docs/pages/product-guides/playground/text-to-speech.mdx index a2f327712..ee3cc2b99 100644 --- a/fern/docs/pages/product-guides/playground/text-to-speech.mdx +++ b/fern/docs/pages/product-guides/playground/text-to-speech.mdx @@ -66,7 +66,7 @@ Not all voices are equal, and a lot depends on the source audio used to create t ElevenLabs offers two families of models: standard (high-quality) models and Flash models, which are optimized for low latency. Each family includes both English-only and multilingual models, tailored for specific use cases with strengths in either speed, accuracy, or language diversity. - + [Learn more about our models](/docs/models) diff --git a/fern/snippets/stt-models.mdx b/fern/snippets/stt-models.mdx new file mode 100644 index 000000000..5ff4a631c --- /dev/null +++ b/fern/snippets/stt-models.mdx @@ -0,0 +1,11 @@ + + + State-of-the-art speech recognition model +
+
Accurate transcription in 99 languages
+
Precise word-level timestamps
+
Speaker diarization
+
Dynamic audio tagging
+
+ + diff --git a/fern/snippets/tts-models.mdx b/fern/snippets/tts-models.mdx new file mode 100644 index 000000000..cdaffc21f --- /dev/null +++ b/fern/snippets/tts-models.mdx @@ -0,0 +1,20 @@ + + + Our most lifelike, emotionally rich speech synthesis model +
+
Most natural-sounding output
+
29 languages supported
+
10,000 character limit
+
Rich emotional expression
+
+ + + Our fast, affordable speech synthesis model +
+
Ultra-low latency (~75ms†)
+
32 languages supported
+
40,000 character limit
+
Faster model, 50% lower price per character
+
+ +