Azure Speech in Foundry Tools
Energize your apps and agents with prebuilt, customizable, multilingual speech AI models.
OVERVIEW
Discover the latest Azure Speech capabilities
- Build voice-enabled, multilingual generative AI apps with fast transcriptions and natural-sounding voices.
- Enable AI agents with end-to-end speech, including customised transcription, voice, and avatars.
- Enable real-time, multi-language speech-to-speech translation and speech-to-text transcription of audio streams.
- Run AI models wherever your data resides. Deploy your apps in the cloud or at the edge with containers.
USE CASES
Develop multimodal generative AI apps with speech models
Build voice-enabled agents
Use foundation models along with customised audio-in and audio-out models to power agents with voice.
Transcribe speech to text
Transcribe call center or meeting conversations. Go global with audio captioning in more than 100 languages.
Convert text to speech
Build bots that speak naturally. Differentiate your brand with customised, realistic voices and speaking styles.
Use post-call analytics
Analyze audio or video call recordings to gain deep insights using foundation models in Azure Content Understanding in Foundry Tools.
Transcribe audio with OpenAI Whisper
Transform your call centers using the latest OpenAI Whisper model in Azure Speech or Azure OpenAI in Foundry Models.
Build custom voices
Build natural-sounding voices with custom neural voice.
Build your avatars
Bring your brand to life using prebuilt or custom avatars with natural-sounding voices.
Enable multilingual communication
Translate audio or video data from and into an ever-growing list of supported languages. Customise translations to your industry.
Embed speech
Use embedded speech to power on-device speech-to-text and text-to-speech scenarios where cloud connectivity is intermittent or unavailable.