AI audio models
Hedra strives to support every state-of-the-art audio model — and is constantly adding new ones as they become available.
All models10 models
ElevenLabs
ElevenLabs Audio IsolationStrip background noise from a recording, keeping the speech.10¢/minuteElevenLabs English STS V216.8¢/minuteElevenLabs Flash Multilingual V2The low-latency voice across 30+ languages, for interactive and high-volume speech.10¢/2,000 charactersElevenLabs Flash V2The low-latency English voice, for interactive speech.10¢/2,000 charactersElevenLabs Multilingual STS V216.8¢/minuteElevenLabs Multilingual V2Steady, natural narration across 30+ languages, for finished voiceover.10¢/1,000 charactersElevenLabs MusicFull tracks from a written brief, with optional lyrics placed across the length you ask for.60¢/minuteElevenLabs Sound EffectsOne-off sound effects from a written description, loopable on request.0.71¢/secondElevenLabs V3The most expressive ElevenLabs voice — emotional range and delivery cues for performance, not just narration.10¢/1,000 charactersElevenLabs Voice CloneUse an audio clip to create a new Voice.Free