Generate AI voiceovers, sound effects, and music using ElevenLabs APIs. Use when creating audio content for videos, podcasts, or games. Triggers include generating voiceovers, narration, dialogue, sound effects from descriptions, background music, soundtrack generation, voice cloning, or any audio s

ElevenLabs Audio Generation Requires ELEVENLABS API KEY in .env . Text to Speech Models Model Quality SSML Support Notes eleven multilingual v2 Highest consistency None Stable, production ready, 29 languages. Toolkit default; supports style + speed eleven v4 Most expressive None (audio tags, IPA) Newest (released 2026 09 28), 90+ languages, best clone accuracy. Stability + similarity only, no style/speed eleven flash v2 5 Good <break , <phoneme Fastest, cheapest; supports pause/pronunciation tags eleven v3 Expressive None Previous generation — prefer v4 Choose: multilingual v2 for reliability and speed/style control, v4 for maximum expressiveness and cloned voices (test a few takes), flash for SSML control. Deprecated: eleven turbo v2 5 → use eleven flash v2 5 (same quality, lower latency; see [deprecated models](https://elevenlabs.io/docs/overview/models deprecated models)). The toolkit still accepts model eleven turbo v2 5 : it prints a one line warning and sends eleven flash v2 5 . Eleven v4 Released 2026 09 28 ([changelog](https://elevenlabs.io/docs/changelog/2026/9/28), [model page](https://elevenlabs.io/docs/overview/capabilities/text to speech/eleven v4 model variants)). The toolkit calls v4 through the Text to Dialogue API with one input (the narrator voice), as ElevenLabs recommends for content creation and long form audio: uv run tools/voiceover.py model eleven v4 ... (and redub.py model eleven v4 ) do this for you, warn once that style / speed are ignored, and split text over ~2,000 chars per request (the reliable dialogue limit) at sentence boundaries. Pace with max wpm instead of speed . client.text to dialogue.convert with timestamps(...) returns the same character alignment as TTS convert with timestamps , so redub.py sync works with v4 and sends the same stability + similarity. Pass settings as a dict: SDK versions before 2.69 type it with a stability only model. The API reads similarity there since 2026 09 28 (it rejects an out of range value with a 422). Text to Dialogue needs elevenlabs =2.21 . Direct delivery with audio tags ( [whispering] , [warm] , [sigh] ) and punctuation. Write tags that clearly describe the voice, because v4 can also read a tag as a sound effect. eleven v4 turbo is the real time variant, available only over the Text to Dialogue WebSocket. The toolkit doesn't use it, since offline renders don't benefit from low latency. Voice Settings by Style Style stability similarity style speed Natural/professional 0.75 0.85 0.9 0.0 0.1 1.0 Conversational 0.5 0.6 0.85 0.3 0.4 0.9 1.0 Energetic/YouTuber 0.3 0.5 0.75 0.5 0.7 1.0 1.1 Pauses Between Sections With flash models: Use SSML break tags inline: Max 3 seconds per break. Excessive breaks can cause speed artifacts. With multilingual v2 / v3 / v4: No SSML support. Options: Paragraph breaks (blank lines) — creates ~0.3 0.5s natural pause v3/v4: audio tags such as [long pause] Post process with ffmpeg: split audio and insert silence WARNING: ... (ellipsis) is NOT a reliable pause — it can be vocalized as a word/sound. Do not use ellipsis as a pause mechanism. Pronunciation Control Phonetic spelling (any model): Write words as you want them pronounced: Janus → Jan us nginx → engine x Use dashes, capitals, apostrophes to guide pronunciation SSML phoneme tags (flash only): IPA in v4: no tags needed. Wrap the IPA in slashes and double quotes in place of the word: Iterative Workflow 1. Generate → listen → identify pronunciation/pacing issues 2. Adjust: phonetic spellings, break tags, voice settings 3. Regenerate. If pauses aren't precise enough, add silence in post with ffmpeg rather than fighting the TTS engine. Speech to Text (Scribe) scribe v2 is current and the toolkit default. scribe v1 is deprecated, with removal announced for 2026 07 09 ([changelog](https://elevenlabs.io/docs/changelog/2026/6/8)), but still answers, so stt model scribe v1 (redub) and model scribe v1 (align captions) still run it, with a warning. scribe v1 experimental , a 2025 preview of scribe v1, is accepted with a warning and sent as scribe v2 . The toolkit uses Scribe in redub.py (transcribe + sync word timing) and align captions.py . Voice Cloning Instant Voice Clone Use client.voices.ivc.create() (not client.voices.clone() ) Pass file handles in binary mode ( "rb" ), not paths Convert m4a first: ffmpeg i input.m4a codec:a libmp3lame qscale:a 2 output.mp3 Multiple samples (2 3 clips) improve accuracy Save voice ID for reuse Professional Voice Clone: Requires Creator plan+, 30+ min audio. See [reference.md](reference.md). Sound Effects Max 22 seconds per generation. Prompt tips: Be specific — "Heavy footsteps on wooden floorboards, slow and deliberate, with creaking" Music Generation 10 seconds to 5 minutes. Use client.music.compose() (not .generate() ). Prompt structure: Genre, mood, instruments, tempo, use case. Add "no vocals" or use force instrumental=True for background music. Remotion Integration Complete Workflow: Script to Synchronized Scene Step 1: Generate Per Scene Audio Use the toolkit's voiceover tool to generate audio for each scene: The manifest.json contains timing info: Step 2: Use Audio in Remotion Composition Step 3: Per Scene Audio (Alternative) For more control, add audio to each scene individually: Syncing Visuals to Voiceover Calculate scene duration from audio, not the other way around: Audio Timing Patterns Voiceover + Demo Video Sync When a scene has both voiceover and demo video: Error Handling Toolkit Command: /generate voiceover The /generate voiceover command handles the full workflow: Popular Voices George: JBFqnCBsd6RMkjVDRZzb (warm narrator) Rachel: 21m00Tcm4TlvDq8ikWAM (clear female) Adam: pNInz6obpgDQGcFmaJgB (professional male) List all: client.voices.get all() For full API docs, see [reference.md](reference.md).