The Next Generation Voicebot Audio Interface
Add audible personality, branding, and emotion to your Alexa or Google Assistant voicebot. Customers respond to Talestreamer-enriched audio interfaces with longer engagement, more repeat usage, and higher reviews. Features include:
Features
| Alexa TTS | Google Assistant TTS | Talestreamer | |
|---|---|---|---|
| Available Voices | 1 per country | 4 per country | 52 |
| Available Languages | 3 | 8 | 18 |
| Supported Audio Format | MP3 48kbps 16kHz | MP3, Ogg/Opus up to 96kbps 24kHz | MP3 up to 128kbps 24kHz |
| Audio Files Per Response | 5 | not documented | 10 |
| Per-Response Voice Selection | No | No | Yes, using TSSS |
| Sound File Transcoding | No | No | Yes |
| Background Music and Effects | No | No | Yes, using TSSS |
| Volume Normalization | No | No | Yes |
| Volume Control | No | No | Yes, using TSSS |
| Sound File Trimming | No | No | Yes, using TSSS |
Customer Feedback
Talestreamer is the result of our experience building and operating The Magic Door since the early days of Alexa skills. More than 500,000 players have spent more than 5,000,000 minutes listening to The Magic Door’s unique combination of human and synthesized voices and foreground and background audio effects.
- “Pretty awesome storytelling with sound effects. I was captivated.”
- “I enjoyed playing it. The sounds make you feel like you are in it.”
- “I was also very impressed that this skill has different sound effects and voices and it just wasn’t Alexa talking the entire time.”
- “…the sound effects are hilarious and they succeed at creating great visial imagery. More fun playing with eyes closed.”
- “The voices and sound effects are awesome. Well done.”
Markup-Driven Audio Synthesis
Talestreamer implements Talestreamer Markup Language (TSML), a proprietary voice markup language that is a superset of SSML, and Talestreamer Stylesheets (TSSS), a voice styling language, like CSS for audio interfaces. Together, TSML and TSSS support:
- Background sounds, including multiple background sounds in a single response
- Independent background and foreground volume control
- Sound file trimming
- Pauses and breaks
- Any SSML supported by Amazon Polly.
Using these features, you can freely mix any combination of brand-related effects, UI hints, voice acted audio, background audio, and synthesized speech. You can do this even while keeping your current SSML markup development workflow.
Easy Cross-Platform Support
Alexa and Google Assistant impose strict and different limits on audio assets, formats, and volume. Talestreamer renders all of your assets into a single response to send to Alexa or Google Assistant, converting and normalizing audio as necessary.
Amazing Life-Like Synthesized Speech
Talestreamer supports all of the AWS Polly voices, in all languages. Contact us if there is a different TTS engine you want to use with Talestreamer.
Pay For What You Use Pricing
With Talestreamer, you pay when you use our tools and APIs, and the generated sounds are yours to use without any restriction by us.
| Basic | Pro | Enterprise | |
|---|---|---|---|
| Free Trial | 30 days | No | No |
| Requests / Month | Up to 25,000 (a successful skill) | Up to 1,000,000 (a very successful skill) | Unlimited |
| TTS Characters / Month | Up to 1,000,000 | Up to 4,000,000 | Unlimited |
| Response Length Limit | 60 seconds | 60 seconds | Unlimited |
| Drop-in integration SDK for Alexa | Yes | Yes | Yes |
| Talestreamer Composer | Yes | Yes | Yes |
| Interactive Testing | Yes | Yes | Yes |
| Audio Download | Yes | Yes | Yes |
| Access to Amazon Polly Voices | Yes | Yes | Yes |
| API Access | Yes | Yes | Yes |
| Price | $4 / month | $16/month | Custom |
Hear the Difference, See the Markup
This TSML generates an audio stream comparing TSML and plain text-to-speech side by side.
More Examples
Please refer to our documentation for more examples.