Skip to content
English
Open Studio
  • There are no suggestions because the search field is empty.

API Features

Our API supports 133+ voices with multiple voice styles and voice customization options.

Here are some of our advanced voice customization features:

  1. Speed: Effortlessly increase or decrease the pace of your voiceovers to ensure they align with the rhythm and flow of the message.
  2. Pitch: Seamlessly adjust the pitch of your voiceovers, adding depth and emotion to your storytelling.
  3. Pause: Easily incorporate strategic pauses in your content to add emphasis, clarity, and a natural cadence to your voiceovers. Example: Hello [pause 1.0s], How are you doing?
  4. Pronunciation: Convey the intended meaning accurately by adapting the pronunciation of words to the nuances of each language. Example: {"live":{"type": "IPA", "pronunciation": "laɪv"}}.
  5. Audio Duration: Control the length of your audio output with the "audioDuration" parameter, aligning your voiceovers precisely with timing requirements in seconds. Example: { "audioDuration": 5 }
  6. Variation: Add variation to your voiceovers through subtle pauses, pitch, and speed changes. The higher the value, the higher the variation. Example: { "variation": 5 }
  7. Multi Native: Enable voices to speak in multiple languages with native fluency by specifying the desired language. Example: { "multiNativeLocale": "en-US" }
  8. Output Formats: Murf supports a wide variety of audio formats, including MP3, WAV, FLAC, ALAW, ULAW, or encode your audio as Base64
  9. Output Quality: Sampling rates include 8Khz, 24Khz, 44.1Khz and 48Khz.

 You can explore all the supported features here. Please explore the Synthesize Speech endpoint to know more about how the voice customization options can be defined for your script. 

Additional API Capabilities

Our API also offers advanced capabilities to support real-time communication, multilingual workflows, and audio transformation use cases.

  • Voice Changer: Transform existing audio recordings into natural-sounding AI voices while preserving the original tone, pacing, and emotion of the speaker. Ideal for replacing manual re-recordings and scaling multilingual or branded voice content.
  • Streaming: Generate and stream audio output in real time using the Falcon model for faster playback and reduced latency in conversational AI, virtual assistants, voice agents, and live applications.
  • WebSockets: Enable low-latency, bidirectional communication for real-time text-to-speech generation. WebSockets are ideal for interactive applications requiring continuous audio streaming and dynamic input handling.
  • Dubbing: Automatically dub audio or video content into multiple languages while maintaining natural voice quality, timing, and speaker consistency for global content localization.
  • Translation: Translate text seamlessly across multiple languages while preserving context and meaning, helping create accurate multilingual voice and content experiences.

You can explore these capabilities and implementation details in our API documentation page.